def MergeMaskedFace(predictor_func, predictor_input_shape, face_enhancer_func, xseg_256_extract_func, cfg, frame_info, img_bgr_uint8, img_bgr, img_face_landmarks): img_size = img_bgr.shape[1], img_bgr.shape[0] img_face_mask_a = LandmarksProcessor.get_image_hull_mask( img_bgr.shape, img_face_landmarks) input_size = predictor_input_shape[0] mask_subres_size = input_size * 4 output_size = input_size if cfg.super_resolution_power != 0: output_size *= 4 face_mat = LandmarksProcessor.get_transform_mat(img_face_landmarks, output_size, face_type=cfg.face_type) face_output_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, output_size, face_type=cfg.face_type, scale=1.0 + 0.01 * cfg.output_face_scale) if mask_subres_size == output_size: face_mask_output_mat = face_output_mat else: face_mask_output_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, mask_subres_size, face_type=cfg.face_type, scale=1.0 + 0.01 * cfg.output_face_scale) dst_face_bgr = cv2.warpAffine(img_bgr, face_mat, (output_size, output_size), flags=cv2.INTER_CUBIC) dst_face_bgr = np.clip(dst_face_bgr, 0, 1) dst_face_mask_a_0 = cv2.warpAffine(img_face_mask_a, face_mat, (output_size, output_size), flags=cv2.INTER_CUBIC) dst_face_mask_a_0 = np.clip(dst_face_mask_a_0, 0, 1) predictor_input_bgr = cv2.resize(dst_face_bgr, (input_size, input_size)) predicted = predictor_func(predictor_input_bgr) prd_face_bgr = np.clip(predicted[0], 0, 1.0) prd_face_mask_a_0 = np.clip(predicted[1], 0, 1.0) prd_face_dst_mask_a_0 = np.clip(predicted[2], 0, 1.0) if cfg.super_resolution_power != 0: prd_face_bgr_enhanced = face_enhancer_func(prd_face_bgr, is_tanh=True, preserve_size=False) mod = cfg.super_resolution_power / 100.0 prd_face_bgr = cv2.resize(prd_face_bgr, (output_size, output_size)) * ( 1.0 - mod) + prd_face_bgr_enhanced * mod prd_face_bgr = np.clip(prd_face_bgr, 0, 1) if cfg.super_resolution_power != 0: prd_face_mask_a_0 = cv2.resize(prd_face_mask_a_0, (output_size, output_size), interpolation=cv2.INTER_CUBIC) prd_face_dst_mask_a_0 = cv2.resize(prd_face_dst_mask_a_0, (output_size, output_size), interpolation=cv2.INTER_CUBIC) if cfg.mask_mode == 1: #dst wrk_face_mask_a_0 = cv2.resize(dst_face_mask_a_0, (output_size, output_size), interpolation=cv2.INTER_CUBIC) elif cfg.mask_mode == 2: #learned-prd wrk_face_mask_a_0 = prd_face_mask_a_0 elif cfg.mask_mode == 3: #learned-dst wrk_face_mask_a_0 = prd_face_dst_mask_a_0 elif cfg.mask_mode == 4: #learned-prd*learned-dst wrk_face_mask_a_0 = prd_face_mask_a_0 * prd_face_dst_mask_a_0 elif cfg.mask_mode == 5: #learned-prd+learned-dst wrk_face_mask_a_0 = np.clip(prd_face_mask_a_0 + prd_face_dst_mask_a_0, 0, 1) elif cfg.mask_mode >= 6 and cfg.mask_mode <= 9: #XSeg modes if cfg.mask_mode == 6 or cfg.mask_mode == 8 or cfg.mask_mode == 9: # obtain XSeg-prd prd_face_xseg_bgr = cv2.resize(prd_face_bgr, (xseg_input_size, ) * 2, interpolation=cv2.INTER_CUBIC) prd_face_xseg_mask = xseg_256_extract_func(prd_face_xseg_bgr) X_prd_face_mask_a_0 = cv2.resize(prd_face_xseg_mask, (output_size, output_size), interpolation=cv2.INTER_CUBIC) if cfg.mask_mode >= 7 and cfg.mask_mode <= 9: # obtain XSeg-dst xseg_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, xseg_input_size, face_type=cfg.face_type) dst_face_xseg_bgr = cv2.warpAffine(img_bgr, xseg_mat, (xseg_input_size, ) * 2, flags=cv2.INTER_CUBIC) dst_face_xseg_mask = xseg_256_extract_func(dst_face_xseg_bgr) X_dst_face_mask_a_0 = cv2.resize(dst_face_xseg_mask, (output_size, output_size), interpolation=cv2.INTER_CUBIC) if cfg.mask_mode == 6: #'XSeg-prd' wrk_face_mask_a_0 = X_prd_face_mask_a_0 elif cfg.mask_mode == 7: #'XSeg-dst' wrk_face_mask_a_0 = X_dst_face_mask_a_0 elif cfg.mask_mode == 8: #'XSeg-prd*XSeg-dst' wrk_face_mask_a_0 = X_prd_face_mask_a_0 * X_dst_face_mask_a_0 elif cfg.mask_mode == 9: #learned-prd*learned-dst*XSeg-prd*XSeg-dst wrk_face_mask_a_0 = prd_face_mask_a_0 * prd_face_dst_mask_a_0 * X_prd_face_mask_a_0 * X_dst_face_mask_a_0 wrk_face_mask_a_0[wrk_face_mask_a_0 < (1.0 / 255.0)] = 0.0 # get rid of noise # resize to mask_subres_size if wrk_face_mask_a_0.shape[0] != mask_subres_size: wrk_face_mask_a_0 = cv2.resize(wrk_face_mask_a_0, (mask_subres_size, mask_subres_size), interpolation=cv2.INTER_CUBIC) # process mask in local predicted space if 'raw' not in cfg.mode: # add zero pad wrk_face_mask_a_0 = np.pad(wrk_face_mask_a_0, input_size) ero = cfg.erode_mask_modifier blur = cfg.blur_mask_modifier if ero > 0: wrk_face_mask_a_0 = cv2.erode(wrk_face_mask_a_0, cv2.getStructuringElement( cv2.MORPH_ELLIPSE, (ero, ero)), iterations=1) elif ero < 0: wrk_face_mask_a_0 = cv2.dilate(wrk_face_mask_a_0, cv2.getStructuringElement( cv2.MORPH_ELLIPSE, (-ero, -ero)), iterations=1) # clip eroded/dilated mask in actual predict area # pad with half blur size in order to accuratelly fade to zero at the boundary clip_size = input_size + blur // 2 wrk_face_mask_a_0[:clip_size, :] = 0 wrk_face_mask_a_0[-clip_size:, :] = 0 wrk_face_mask_a_0[:, :clip_size] = 0 wrk_face_mask_a_0[:, -clip_size:] = 0 if blur > 0: blur = blur + (1 - blur % 2) wrk_face_mask_a_0 = cv2.GaussianBlur(wrk_face_mask_a_0, (blur, blur), 0) wrk_face_mask_a_0 = wrk_face_mask_a_0[input_size:-input_size, input_size:-input_size] wrk_face_mask_a_0 = np.clip(wrk_face_mask_a_0, 0, 1) img_face_mask_a = cv2.warpAffine(wrk_face_mask_a_0, face_mask_output_mat, img_size, np.zeros(img_bgr.shape[0:2], dtype=np.float32), flags=cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC)[..., None] img_face_mask_a = np.clip(img_face_mask_a, 0.0, 1.0) img_face_mask_a[img_face_mask_a < (1.0 / 255.0)] = 0.0 # get rid of noise if wrk_face_mask_a_0.shape[0] != output_size: wrk_face_mask_a_0 = cv2.resize(wrk_face_mask_a_0, (output_size, output_size), interpolation=cv2.INTER_CUBIC) wrk_face_mask_a = wrk_face_mask_a_0[..., None] out_img = None out_merging_mask_a = None if cfg.mode == 'original': return img_bgr, img_face_mask_a elif 'raw' in cfg.mode: if cfg.mode == 'raw-rgb': out_img_face = cv2.warpAffine( prd_face_bgr, face_output_mat, img_size, np.empty_like(img_bgr), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC) out_img_face_mask = cv2.warpAffine( np.ones_like(prd_face_bgr), face_output_mat, img_size, np.empty_like(img_bgr), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC) out_img = img_bgr * ( 1 - out_img_face_mask) + out_img_face * out_img_face_mask out_merging_mask_a = img_face_mask_a elif cfg.mode == 'raw-predict': out_img = prd_face_bgr out_merging_mask_a = wrk_face_mask_a else: raise ValueError(f"undefined raw type {cfg.mode}") out_img = np.clip(out_img, 0.0, 1.0) else: # Process if the mask meets minimum size maxregion = np.argwhere(img_face_mask_a >= 0.1) if maxregion.size != 0: miny, minx = maxregion.min(axis=0)[:2] maxy, maxx = maxregion.max(axis=0)[:2] lenx = maxx - minx leny = maxy - miny if min(lenx, leny) >= 4: wrk_face_mask_area_a = wrk_face_mask_a.copy() wrk_face_mask_area_a[wrk_face_mask_area_a > 0] = 1.0 if 'seamless' not in cfg.mode and cfg.color_transfer_mode != 0: if cfg.color_transfer_mode == 1: #rct prd_face_bgr = imagelib.reinhard_color_transfer( np.clip(prd_face_bgr * wrk_face_mask_area_a * 255, 0, 255).astype(np.uint8), np.clip(dst_face_bgr * wrk_face_mask_area_a * 255, 0, 255).astype(np.uint8), ) prd_face_bgr = np.clip( prd_face_bgr.astype(np.float32) / 255.0, 0.0, 1.0) elif cfg.color_transfer_mode == 2: #lct prd_face_bgr = imagelib.linear_color_transfer( prd_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 3: #mkl prd_face_bgr = imagelib.color_transfer_mkl( prd_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 4: #mkl-m prd_face_bgr = imagelib.color_transfer_mkl( prd_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a) elif cfg.color_transfer_mode == 5: #idt prd_face_bgr = imagelib.color_transfer_idt( prd_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 6: #idt-m prd_face_bgr = imagelib.color_transfer_idt( prd_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a) elif cfg.color_transfer_mode == 7: #sot-m prd_face_bgr = imagelib.color_transfer_sot( prd_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a, steps=10, batch_size=30) prd_face_bgr = np.clip(prd_face_bgr, 0.0, 1.0) elif cfg.color_transfer_mode == 8: #mix-m prd_face_bgr = imagelib.color_transfer_mix( prd_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a) if cfg.mode == 'hist-match': hist_mask_a = np.ones(prd_face_bgr.shape[:2] + (1, ), dtype=np.float32) if cfg.masked_hist_match: hist_mask_a *= wrk_face_mask_area_a white = (1.0 - hist_mask_a) * np.ones( prd_face_bgr.shape[:2] + (1, ), dtype=np.float32) hist_match_1 = prd_face_bgr * hist_mask_a + white hist_match_1[hist_match_1 > 1.0] = 1.0 hist_match_2 = dst_face_bgr * hist_mask_a + white hist_match_2[hist_match_1 > 1.0] = 1.0 prd_face_bgr = imagelib.color_hist_match( hist_match_1, hist_match_2, cfg.hist_match_threshold).astype(dtype=np.float32) if 'seamless' in cfg.mode: #mask used for cv2.seamlessClone img_face_seamless_mask_a = None for i in range(1, 10): a = img_face_mask_a > i / 10.0 if len(np.argwhere(a)) == 0: continue img_face_seamless_mask_a = img_face_mask_a.copy() img_face_seamless_mask_a[a] = 1.0 img_face_seamless_mask_a[ img_face_seamless_mask_a <= i / 10.0] = 0.0 break out_img = cv2.warpAffine( prd_face_bgr, face_output_mat, img_size, np.empty_like(img_bgr), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC) out_img = np.clip(out_img, 0.0, 1.0) if 'seamless' in cfg.mode: try: #calc same bounding rect and center point as in cv2.seamlessClone to prevent jittering (not flickering) l, t, w, h = cv2.boundingRect( (img_face_seamless_mask_a * 255).astype(np.uint8)) s_maskx, s_masky = int(l + w / 2), int(t + h / 2) out_img = cv2.seamlessClone( (out_img * 255).astype(np.uint8), img_bgr_uint8, (img_face_seamless_mask_a * 255).astype(np.uint8), (s_maskx, s_masky), cv2.NORMAL_CLONE) out_img = out_img.astype(dtype=np.float32) / 255.0 except Exception as e: #seamlessClone may fail in some cases e_str = traceback.format_exc() if 'MemoryError' in e_str: raise Exception( "Seamless fail: " + e_str ) #reraise MemoryError in order to reprocess this data by other processes else: print("Seamless fail: " + e_str) cfg_mp = cfg.motion_blur_power / 100.0 out_img = img_bgr * (1 - img_face_mask_a) + (out_img * img_face_mask_a) if ('seamless' in cfg.mode and cfg.color_transfer_mode != 0) or \ cfg.mode == 'seamless-hist-match' or \ cfg_mp != 0 or \ cfg.blursharpen_amount != 0 or \ cfg.image_denoise_power != 0 or \ cfg.bicubic_degrade_power != 0: out_face_bgr = cv2.warpAffine(out_img, face_mat, (output_size, output_size), flags=cv2.INTER_CUBIC) if 'seamless' in cfg.mode and cfg.color_transfer_mode != 0: if cfg.color_transfer_mode == 1: out_face_bgr = imagelib.reinhard_color_transfer( np.clip( out_face_bgr * wrk_face_mask_area_a * 255, 0, 255).astype(np.uint8), np.clip( dst_face_bgr * wrk_face_mask_area_a * 255, 0, 255).astype(np.uint8)) out_face_bgr = np.clip( out_face_bgr.astype(np.float32) / 255.0, 0.0, 1.0) elif cfg.color_transfer_mode == 2: #lct out_face_bgr = imagelib.linear_color_transfer( out_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 3: #mkl out_face_bgr = imagelib.color_transfer_mkl( out_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 4: #mkl-m out_face_bgr = imagelib.color_transfer_mkl( out_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a) elif cfg.color_transfer_mode == 5: #idt out_face_bgr = imagelib.color_transfer_idt( out_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 6: #idt-m out_face_bgr = imagelib.color_transfer_idt( out_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a) elif cfg.color_transfer_mode == 7: #sot-m out_face_bgr = imagelib.color_transfer_sot( out_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a, steps=10, batch_size=30) out_face_bgr = np.clip(out_face_bgr, 0.0, 1.0) elif cfg.color_transfer_mode == 8: #mix-m out_face_bgr = imagelib.color_transfer_mix( out_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a) if cfg.mode == 'seamless-hist-match': out_face_bgr = imagelib.color_hist_match( out_face_bgr, dst_face_bgr, cfg.hist_match_threshold) if cfg_mp != 0: k_size = int(frame_info.motion_power * cfg_mp) if k_size >= 1: k_size = np.clip(k_size + 1, 2, 50) if cfg.super_resolution_power != 0: k_size *= 2 out_face_bgr = imagelib.LinearMotionBlur( out_face_bgr, k_size, frame_info.motion_deg) if cfg.blursharpen_amount != 0: out_face_bgr = imagelib.blursharpen( out_face_bgr, cfg.sharpen_mode, 3, cfg.blursharpen_amount) if cfg.image_denoise_power != 0: n = cfg.image_denoise_power while n > 0: img_bgr_denoised = cv2.medianBlur(img_bgr, 5) if int(n / 100) != 0: img_bgr = img_bgr_denoised else: pass_power = (n % 100) / 100.0 img_bgr = img_bgr * ( 1.0 - pass_power) + img_bgr_denoised * pass_power n = max(n - 10, 0) if cfg.bicubic_degrade_power != 0: p = 1.0 - cfg.bicubic_degrade_power / 101.0 img_bgr_downscaled = cv2.resize( img_bgr, (int(img_size[0] * p), int(img_size[1] * p)), interpolation=cv2.INTER_CUBIC) img_bgr = cv2.resize(img_bgr_downscaled, img_size, interpolation=cv2.INTER_CUBIC) new_out = cv2.warpAffine( out_face_bgr, face_mat, img_size, np.empty_like(img_bgr), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC) out_img = np.clip( img_bgr * (1 - img_face_mask_a) + (new_out * img_face_mask_a), 0, 1.0) if cfg.color_degrade_power != 0: out_img_reduced = imagelib.reduce_colors(out_img, 256) if cfg.color_degrade_power == 100: out_img = out_img_reduced else: alpha = cfg.color_degrade_power / 100.0 out_img = (out_img * (1.0 - alpha) + out_img_reduced * alpha) out_merging_mask_a = img_face_mask_a if out_img is None: out_img = img_bgr.copy() return out_img, out_merging_mask_a
def MergeMaskedFace(predictor_func, predictor_input_shape, cfg, frame_info, img_bgr_uint8, img_bgr, img_face_landmarks): img_size = img_bgr.shape[1], img_bgr.shape[0] img_face_mask_a = LandmarksProcessor.get_image_hull_mask( img_bgr.shape, img_face_landmarks) if cfg.mode == 'original': return img_bgr, img_face_mask_a out_img = img_bgr.copy() out_merging_mask_a = None input_size = predictor_input_shape[0] mask_subres_size = input_size * 4 output_size = input_size if cfg.super_resolution_power != 0: output_size *= 4 face_mat = LandmarksProcessor.get_transform_mat(img_face_landmarks, output_size, face_type=cfg.face_type) face_output_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, output_size, face_type=cfg.face_type, scale=1.0 + 0.01 * cfg.output_face_scale) if mask_subres_size == output_size: face_mask_output_mat = face_output_mat else: face_mask_output_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, mask_subres_size, face_type=cfg.face_type, scale=1.0 + 0.01 * cfg.output_face_scale) dst_face_bgr = cv2.warpAffine(img_bgr, face_mat, (output_size, output_size), flags=cv2.INTER_CUBIC) dst_face_bgr = np.clip(dst_face_bgr, 0, 1) dst_face_mask_a_0 = cv2.warpAffine(img_face_mask_a, face_mat, (output_size, output_size), flags=cv2.INTER_CUBIC) dst_face_mask_a_0 = np.clip(dst_face_mask_a_0, 0, 1) predictor_input_bgr = cv2.resize(dst_face_bgr, (input_size, input_size)) predicted = predictor_func(predictor_input_bgr) if isinstance(predicted, tuple): #merger return bgr,mask prd_face_bgr = np.clip(predicted[0], 0, 1.0) prd_face_mask_a_0 = np.clip(predicted[1], 0, 1.0) predictor_masked = True else: #merger return bgr only, using dst mask prd_face_bgr = np.clip(predicted, 0, 1.0) prd_face_mask_a_0 = cv2.resize(dst_face_mask_a_0, (input_size, input_size)) predictor_masked = False if cfg.super_resolution_power != 0: prd_face_bgr_enhanced = cfg.superres_func(prd_face_bgr) mod = cfg.super_resolution_power / 100.0 prd_face_bgr = cv2.resize(prd_face_bgr, (output_size, output_size)) * ( 1.0 - mod) + prd_face_bgr_enhanced * mod prd_face_bgr = np.clip(prd_face_bgr, 0, 1) if cfg.super_resolution_power != 0: if predictor_masked: prd_face_mask_a_0 = cv2.resize(prd_face_mask_a_0, (output_size, output_size), cv2.INTER_CUBIC) else: prd_face_mask_a_0 = cv2.resize(dst_face_mask_a_0, (output_size, output_size), cv2.INTER_CUBIC) if cfg.mask_mode == 2: #dst prd_face_mask_a_0 = cv2.resize(dst_face_mask_a_0, (output_size, output_size), cv2.INTER_CUBIC) elif cfg.mask_mode >= 3 and cfg.mask_mode <= 8: if cfg.mask_mode == 3 or cfg.mask_mode == 5 or cfg.mask_mode == 6: prd_face_fanseg_bgr = cv2.resize(prd_face_bgr, (cfg.fanseg_input_size, ) * 2) prd_face_fanseg_mask = cfg.fanseg_extract_func( FaceType.FULL, prd_face_fanseg_bgr) FAN_prd_face_mask_a_0 = cv2.resize(prd_face_fanseg_mask, (output_size, output_size), cv2.INTER_CUBIC) if cfg.mask_mode >= 4 and cfg.mask_mode <= 7: full_face_fanseg_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, cfg.fanseg_input_size, face_type=FaceType.FULL) dst_face_fanseg_bgr = cv2.warpAffine(img_bgr, full_face_fanseg_mat, (cfg.fanseg_input_size, ) * 2, flags=cv2.INTER_CUBIC) dst_face_fanseg_mask = cfg.fanseg_extract_func( FaceType.FULL, dst_face_fanseg_bgr) if cfg.face_type == FaceType.FULL: FAN_dst_face_mask_a_0 = cv2.resize(dst_face_fanseg_mask, (output_size, output_size), cv2.INTER_CUBIC) else: face_fanseg_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, cfg.fanseg_input_size, face_type=cfg.face_type) fanseg_rect_corner_pts = np.array( [[0, 0], [cfg.fanseg_input_size - 1, 0], [0, cfg.fanseg_input_size - 1]], dtype=np.float32) a = LandmarksProcessor.transform_points(fanseg_rect_corner_pts, face_fanseg_mat, invert=True) b = LandmarksProcessor.transform_points( a, full_face_fanseg_mat) m = cv2.getAffineTransform(b, fanseg_rect_corner_pts) FAN_dst_face_mask_a_0 = cv2.warpAffine( dst_face_fanseg_mask, m, (cfg.fanseg_input_size, ) * 2, flags=cv2.INTER_CUBIC) FAN_dst_face_mask_a_0 = cv2.resize(FAN_dst_face_mask_a_0, (output_size, output_size), cv2.INTER_CUBIC) if cfg.mask_mode == 3: #FAN-prd prd_face_mask_a_0 = FAN_prd_face_mask_a_0 elif cfg.mask_mode == 4: #FAN-dst prd_face_mask_a_0 = FAN_dst_face_mask_a_0 elif cfg.mask_mode == 5: prd_face_mask_a_0 = FAN_prd_face_mask_a_0 * FAN_dst_face_mask_a_0 elif cfg.mask_mode == 6: prd_face_mask_a_0 = prd_face_mask_a_0 * FAN_prd_face_mask_a_0 * FAN_dst_face_mask_a_0 elif cfg.mask_mode == 7: prd_face_mask_a_0 = prd_face_mask_a_0 * FAN_dst_face_mask_a_0 prd_face_mask_a_0[prd_face_mask_a_0 < (1.0 / 255.0)] = 0.0 # get rid of noise # resize to mask_subres_size if prd_face_mask_a_0.shape[0] != mask_subres_size: prd_face_mask_a_0 = cv2.resize(prd_face_mask_a_0, (mask_subres_size, mask_subres_size), cv2.INTER_CUBIC) # process mask in local predicted space if 'raw' not in cfg.mode: # add zero pad prd_face_mask_a_0 = np.pad(prd_face_mask_a_0, input_size) ero = cfg.erode_mask_modifier blur = cfg.blur_mask_modifier if ero > 0: prd_face_mask_a_0 = cv2.erode(prd_face_mask_a_0, cv2.getStructuringElement( cv2.MORPH_ELLIPSE, (ero, ero)), iterations=1) elif ero < 0: prd_face_mask_a_0 = cv2.dilate(prd_face_mask_a_0, cv2.getStructuringElement( cv2.MORPH_ELLIPSE, (-ero, -ero)), iterations=1) # clip eroded/dilated mask in actual predict area # pad with half blur size in order to accuratelly fade to zero at the boundary clip_size = input_size + blur // 2 prd_face_mask_a_0[:clip_size, :] = 0 prd_face_mask_a_0[-clip_size:, :] = 0 prd_face_mask_a_0[:, :clip_size] = 0 prd_face_mask_a_0[:, -clip_size:] = 0 if blur > 0: blur = blur + (1 - blur % 2) prd_face_mask_a_0 = cv2.GaussianBlur(prd_face_mask_a_0, (blur, blur), 0) prd_face_mask_a_0 = prd_face_mask_a_0[input_size:-input_size, input_size:-input_size] prd_face_mask_a_0 = np.clip(prd_face_mask_a_0, 0, 1) img_face_mask_a = cv2.warpAffine(prd_face_mask_a_0, face_mask_output_mat, img_size, np.zeros(img_bgr.shape[0:2], dtype=np.float32), flags=cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC)[..., None] img_face_mask_a = np.clip(img_face_mask_a, 0.0, 1.0) img_face_mask_a[img_face_mask_a < (1.0 / 255.0)] = 0.0 # get rid of noise if prd_face_mask_a_0.shape[0] != output_size: prd_face_mask_a_0 = cv2.resize(prd_face_mask_a_0, (output_size, output_size), cv2.INTER_CUBIC) prd_face_mask_a = prd_face_mask_a_0[..., None] prd_face_mask_area_a = prd_face_mask_a.copy() prd_face_mask_area_a[prd_face_mask_area_a > 0] = 1.0 if 'raw' in cfg.mode: if cfg.mode == 'raw-rgb': out_img = cv2.warpAffine(prd_face_bgr, face_output_mat, img_size, out_img, cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT) out_merging_mask_a = img_face_mask_a out_img = np.clip(out_img, 0.0, 1.0) else: #averaging [lenx, leny, maskx, masky] by grayscale gradients of upscaled mask ar = [] for i in range(1, 10): maxregion = np.argwhere(img_face_mask_a > i / 10.0) if maxregion.size != 0: miny, minx = maxregion.min(axis=0)[:2] maxy, maxx = maxregion.max(axis=0)[:2] lenx = maxx - minx leny = maxy - miny if min(lenx, leny) >= 4: ar += [[lenx, leny]] if len(ar) > 0: if 'seamless' not in cfg.mode and cfg.color_transfer_mode != 0: if cfg.color_transfer_mode == 1: #rct prd_face_bgr = imagelib.reinhard_color_transfer( np.clip(prd_face_bgr * prd_face_mask_area_a * 255, 0, 255).astype(np.uint8), np.clip(dst_face_bgr * prd_face_mask_area_a * 255, 0, 255).astype(np.uint8), ) prd_face_bgr = np.clip( prd_face_bgr.astype(np.float32) / 255.0, 0.0, 1.0) elif cfg.color_transfer_mode == 2: #lct prd_face_bgr = imagelib.linear_color_transfer( prd_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 3: #mkl prd_face_bgr = imagelib.color_transfer_mkl( prd_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 4: #mkl-m prd_face_bgr = imagelib.color_transfer_mkl( prd_face_bgr * prd_face_mask_area_a, dst_face_bgr * prd_face_mask_area_a) elif cfg.color_transfer_mode == 5: #idt prd_face_bgr = imagelib.color_transfer_idt( prd_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 6: #idt-m prd_face_bgr = imagelib.color_transfer_idt( prd_face_bgr * prd_face_mask_area_a, dst_face_bgr * prd_face_mask_area_a) elif cfg.color_transfer_mode == 7: #sot-m prd_face_bgr = imagelib.color_transfer_sot( prd_face_bgr * prd_face_mask_area_a, dst_face_bgr * prd_face_mask_area_a) prd_face_bgr = np.clip(prd_face_bgr, 0.0, 1.0) elif cfg.color_transfer_mode == 8: #mix-m prd_face_bgr = imagelib.color_transfer_mix( prd_face_bgr * prd_face_mask_area_a, dst_face_bgr * prd_face_mask_area_a) if cfg.mode == 'hist-match': hist_mask_a = np.ones(prd_face_bgr.shape[:2] + (1, ), dtype=np.float32) if cfg.masked_hist_match: hist_mask_a *= prd_face_mask_area_a white = (1.0 - hist_mask_a) * np.ones( prd_face_bgr.shape[:2] + (1, ), dtype=np.float32) hist_match_1 = prd_face_bgr * hist_mask_a + white hist_match_1[hist_match_1 > 1.0] = 1.0 hist_match_2 = dst_face_bgr * hist_mask_a + white hist_match_2[hist_match_1 > 1.0] = 1.0 prd_face_bgr = imagelib.color_hist_match( hist_match_1, hist_match_2, cfg.hist_match_threshold).astype(dtype=np.float32) if 'seamless' in cfg.mode: #mask used for cv2.seamlessClone img_face_seamless_mask_a = None for i in range(1, 10): a = img_face_mask_a > i / 10.0 if len(np.argwhere(a)) == 0: continue img_face_seamless_mask_a = img_face_mask_a.copy() img_face_seamless_mask_a[a] = 1.0 img_face_seamless_mask_a[img_face_seamless_mask_a <= i / 10.0] = 0.0 break out_img = cv2.warpAffine(prd_face_bgr, face_output_mat, img_size, out_img, cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT) out_img = np.clip(out_img, 0.0, 1.0) if 'seamless' in cfg.mode: try: #calc same bounding rect and center point as in cv2.seamlessClone to prevent jittering (not flickering) l, t, w, h = cv2.boundingRect( (img_face_seamless_mask_a * 255).astype(np.uint8)) s_maskx, s_masky = int(l + w / 2), int(t + h / 2) out_img = cv2.seamlessClone( (out_img * 255).astype(np.uint8), img_bgr_uint8, (img_face_seamless_mask_a * 255).astype(np.uint8), (s_maskx, s_masky), cv2.NORMAL_CLONE) out_img = out_img.astype(dtype=np.float32) / 255.0 except Exception as e: #seamlessClone may fail in some cases e_str = traceback.format_exc() if 'MemoryError' in e_str: raise Exception( "Seamless fail: " + e_str ) #reraise MemoryError in order to reprocess this data by other processes else: print("Seamless fail: " + e_str) out_img = img_bgr * (1 - img_face_mask_a) + (out_img * img_face_mask_a) out_face_bgr = cv2.warpAffine(out_img, face_mat, (output_size, output_size), flags=cv2.INTER_CUBIC) if 'seamless' in cfg.mode and cfg.color_transfer_mode != 0: if cfg.color_transfer_mode == 1: out_face_bgr = imagelib.reinhard_color_transfer( np.clip(out_face_bgr * prd_face_mask_area_a * 255, 0, 255).astype(np.uint8), np.clip(dst_face_bgr * prd_face_mask_area_a * 255, 0, 255).astype(np.uint8)) out_face_bgr = np.clip( out_face_bgr.astype(np.float32) / 255.0, 0.0, 1.0) elif cfg.color_transfer_mode == 2: #lct out_face_bgr = imagelib.linear_color_transfer( out_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 3: #mkl out_face_bgr = imagelib.color_transfer_mkl( out_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 4: #mkl-m out_face_bgr = imagelib.color_transfer_mkl( out_face_bgr * prd_face_mask_area_a, dst_face_bgr * prd_face_mask_area_a) elif cfg.color_transfer_mode == 5: #idt out_face_bgr = imagelib.color_transfer_idt( out_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 6: #idt-m out_face_bgr = imagelib.color_transfer_idt( out_face_bgr * prd_face_mask_area_a, dst_face_bgr * prd_face_mask_area_a) elif cfg.color_transfer_mode == 7: #sot-m out_face_bgr = imagelib.color_transfer_sot( out_face_bgr * prd_face_mask_area_a, dst_face_bgr * prd_face_mask_area_a) out_face_bgr = np.clip(out_face_bgr, 0.0, 1.0) elif cfg.color_transfer_mode == 8: #mix-m out_face_bgr = imagelib.color_transfer_mix( out_face_bgr * prd_face_mask_area_a, dst_face_bgr * prd_face_mask_area_a) if cfg.mode == 'seamless-hist-match': out_face_bgr = imagelib.color_hist_match( out_face_bgr, dst_face_bgr, cfg.hist_match_threshold) cfg_mp = cfg.motion_blur_power / 100.0 if cfg_mp != 0: k_size = int(frame_info.motion_power * cfg_mp) if k_size >= 1: k_size = np.clip(k_size + 1, 2, 50) if cfg.super_resolution_power != 0: k_size *= 2 out_face_bgr = imagelib.LinearMotionBlur( out_face_bgr, k_size, frame_info.motion_deg) if cfg.blursharpen_amount != 0: out_face_bgr = cfg.blursharpen_func(out_face_bgr, cfg.sharpen_mode, 3, cfg.blursharpen_amount) if cfg.image_denoise_power != 0: n = cfg.image_denoise_power while n > 0: img_bgr_denoised = cv2.medianBlur(img_bgr, 5) if int(n / 100) != 0: img_bgr = img_bgr_denoised else: pass_power = (n % 100) / 100.0 img_bgr = img_bgr * ( 1.0 - pass_power) + img_bgr_denoised * pass_power n = max(n - 10, 0) if cfg.bicubic_degrade_power != 0: p = 1.0 - cfg.bicubic_degrade_power / 101.0 img_bgr_downscaled = cv2.resize( img_bgr, (int(img_size[0] * p), int(img_size[1] * p)), cv2.INTER_CUBIC) img_bgr = cv2.resize(img_bgr_downscaled, img_size, cv2.INTER_CUBIC) new_out = cv2.warpAffine(out_face_bgr, face_mat, img_size, img_bgr.copy(), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT) out_img = np.clip( img_bgr * (1 - img_face_mask_a) + (new_out * img_face_mask_a), 0, 1.0) if cfg.color_degrade_power != 0: out_img_reduced = imagelib.reduce_colors(out_img, 256) if cfg.color_degrade_power == 100: out_img = out_img_reduced else: alpha = cfg.color_degrade_power / 100.0 out_img = (out_img * (1.0 - alpha) + out_img_reduced * alpha) out_merging_mask_a = img_face_mask_a return out_img, out_merging_mask_a
def process(samples, sample_process_options, output_sample_types, debug, ct_sample=None): SPTF = SampleProcessor.Types sample_rnd_seed = np.random.randint(0x80000000) outputs = [] for sample in samples: sample_bgr = sample.load_bgr() ct_sample_bgr = None ct_sample_mask = None h, w, c = sample_bgr.shape is_face_sample = sample.landmarks is not None if debug and is_face_sample: LandmarksProcessor.draw_landmarks(sample_bgr, sample.landmarks, (0, 1, 0)) params = imagelib.gen_warp_params( sample_bgr, sample_process_options.random_flip, rotation_range=sample_process_options.rotation_range, scale_range=sample_process_options.scale_range, tx_range=sample_process_options.tx_range, ty_range=sample_process_options.ty_range, rnd_seed=sample_rnd_seed) outputs_sample = [] for opts in output_sample_types: resolution = opts.get('resolution', 0) types = opts.get('types', []) border_replicate = opts.get('border_replicate', True) random_sub_res = opts.get('random_sub_res', 0) normalize_std_dev = opts.get('normalize_std_dev', False) normalize_vgg = opts.get('normalize_vgg', False) motion_blur = opts.get('motion_blur', None) gaussian_blur = opts.get('gaussian_blur', None) ct_mode = opts.get('ct_mode', 'None') normalize_tanh = opts.get('normalize_tanh', False) data_format = opts.get('data_format', 'NHWC') img_type = SPTF.NONE target_face_type = SPTF.NONE face_mask_type = SPTF.NONE mode_type = SPTF.NONE for t in types: if t >= SPTF.IMG_TYPE_BEGIN and t < SPTF.IMG_TYPE_END: img_type = t elif t >= SPTF.FACE_TYPE_BEGIN and t < SPTF.FACE_TYPE_END: target_face_type = t elif t >= SPTF.MODE_BEGIN and t < SPTF.MODE_END: mode_type = t if img_type == SPTF.NONE: raise ValueError('expected IMG_ type') if img_type == SPTF.IMG_LANDMARKS_ARRAY: l = sample.landmarks l = np.concatenate([ np.expand_dims(l[:, 0] / w, -1), np.expand_dims(l[:, 1] / h, -1) ], -1) l = np.clip(l, 0.0, 1.0) img = l elif img_type == SPTF.IMG_PITCH_YAW_ROLL or img_type == SPTF.IMG_PITCH_YAW_ROLL_SIGMOID: pitch_yaw_roll = sample.get_pitch_yaw_roll() if params['flip']: yaw = -yaw if img_type == SPTF.IMG_PITCH_YAW_ROLL_SIGMOID: pitch = np.clip((pitch / math.pi) / 2.0 + 1.0, 0, 1) yaw = np.clip((yaw / math.pi) / 2.0 + 1.0, 0, 1) roll = np.clip((roll / math.pi) / 2.0 + 1.0, 0, 1) img = (pitch, yaw, roll) else: if mode_type == SPTF.NONE: raise ValueError('expected MODE_ type') def do_transform(img, mask): warp = (img_type == SPTF.IMG_WARPED or img_type == SPTF.IMG_WARPED_TRANSFORMED) transform = (img_type == SPTF.IMG_WARPED_TRANSFORMED or img_type == SPTF.IMG_TRANSFORMED) flip = img_type != SPTF.IMG_WARPED img = imagelib.warp_by_params(params, img, warp, transform, flip, border_replicate) if mask is not None: mask = imagelib.warp_by_params( params, mask, warp, transform, flip, False) if len(mask.shape) == 2: mask = mask[..., np.newaxis] return img, mask img = sample_bgr ### Prepare a mask mask = None if is_face_sample: if sample.eyebrows_expand_mod is not None: mask = LandmarksProcessor.get_image_hull_mask( img.shape, sample.landmarks, eyebrows_expand_mod=sample.eyebrows_expand_mod) else: mask = LandmarksProcessor.get_image_hull_mask( img.shape, sample.landmarks) if sample.ie_polys is not None: sample.ie_polys.overlay_mask(mask) ################## if motion_blur is not None: chance, mb_max_size = motion_blur chance = np.clip(chance, 0, 100) if np.random.randint(100) < chance: img = imagelib.LinearMotionBlur( img, np.random.randint(mb_max_size) + 1, np.random.randint(360)) if gaussian_blur is not None: chance, kernel_max_size = gaussian_blur chance = np.clip(chance, 0, 100) if np.random.randint(100) < chance: img = cv2.GaussianBlur( img, (np.random.randint(kernel_max_size) * 2 + 1, ) * 2, 0) if is_face_sample and target_face_type != SPTF.NONE: target_ft = SampleProcessor.SPTF_FACETYPE_TO_FACETYPE[ target_face_type] if target_ft > sample.face_type: raise Exception( 'sample %s type %s does not match model requirement %s. Consider extract necessary type of faces.' % (sample.filename, sample.face_type, target_ft)) if sample.face_type == FaceType.MARK_ONLY: #first warp to target facetype img = cv2.warpAffine( img, LandmarksProcessor.get_transform_mat( sample.landmarks, sample.shape[0], target_ft), (sample.shape[0], sample.shape[0]), flags=cv2.INTER_CUBIC) mask = cv2.warpAffine( mask, LandmarksProcessor.get_transform_mat( sample.landmarks, sample.shape[0], target_ft), (sample.shape[0], sample.shape[0]), flags=cv2.INTER_CUBIC) #then apply transforms img, mask = do_transform(img, mask) img = np.concatenate((img, mask), -1) img = cv2.resize(img, (resolution, resolution), cv2.INTER_CUBIC) else: img, mask = do_transform(img, mask) mat = LandmarksProcessor.get_transform_mat( sample.landmarks, resolution, target_ft) img = cv2.warpAffine( img, mat, (resolution, resolution), borderMode=(cv2.BORDER_REPLICATE if border_replicate else cv2.BORDER_CONSTANT), flags=cv2.INTER_CUBIC) mask = cv2.warpAffine( mask, mat, (resolution, resolution), borderMode=cv2.BORDER_CONSTANT, flags=cv2.INTER_CUBIC) img = np.concatenate((img, mask[..., None]), -1) else: img, mask = do_transform(img, mask) img = np.concatenate((img, mask), -1) img = cv2.resize(img, (resolution, resolution), cv2.INTER_CUBIC) if random_sub_res != 0: sub_size = resolution - random_sub_res rnd_state = np.random.RandomState(sample_rnd_seed + random_sub_res) start_x = rnd_state.randint(sub_size + 1) start_y = rnd_state.randint(sub_size + 1) img = img[start_y:start_y + sub_size, start_x:start_x + sub_size, :] img = np.clip(img, 0, 1).astype(np.float32) img_bgr = img[..., 0:3] img_mask = img[..., 3:4] if ct_mode is not None and ct_sample is not None: if ct_sample_bgr is None: ct_sample_bgr = ct_sample.load_bgr() ct_sample_bgr_resized = cv2.resize( ct_sample_bgr, (resolution, resolution), cv2.INTER_LINEAR) if ct_mode == 'lct': img_bgr = imagelib.linear_color_transfer( img_bgr, ct_sample_bgr_resized) img_bgr = np.clip(img_bgr, 0.0, 1.0) elif ct_mode == 'rct': img_bgr = imagelib.reinhard_color_transfer( np.clip((img_bgr * 255).astype(np.uint8), 0, 255), np.clip((ct_sample_bgr_resized * 255).astype( np.uint8), 0, 255)) img_bgr = np.clip( img_bgr.astype(np.float32) / 255.0, 0.0, 1.0) elif ct_mode == 'mkl': img_bgr = imagelib.color_transfer_mkl( img_bgr, ct_sample_bgr_resized) elif ct_mode == 'idt': img_bgr = imagelib.color_transfer_idt( img_bgr, ct_sample_bgr_resized) elif ct_mode == 'sot': img_bgr = imagelib.color_transfer_sot( img_bgr, ct_sample_bgr_resized) img_bgr = np.clip(img_bgr, 0.0, 1.0) if normalize_std_dev: img_bgr = (img_bgr - img_bgr.mean( (0, 1))) / img_bgr.std((0, 1)) elif normalize_vgg: img_bgr = np.clip(img_bgr * 255, 0, 255) img_bgr[:, :, 0] -= 103.939 img_bgr[:, :, 1] -= 116.779 img_bgr[:, :, 2] -= 123.68 if mode_type == SPTF.MODE_BGR: img = img_bgr elif mode_type == SPTF.MODE_BGR_SHUFFLE: rnd_state = np.random.RandomState(sample_rnd_seed) img = np.take(img_bgr, rnd_state.permutation(img_bgr.shape[-1]), axis=-1) elif mode_type == SPTF.MODE_BGR_RANDOM_HSV_SHIFT: rnd_state = np.random.RandomState(sample_rnd_seed) hsv = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2HSV) h, s, v = cv2.split(hsv) h = (h + rnd_state.randint(360)) % 360 s = np.clip(s + rnd_state.random() - 0.5, 0, 1) v = np.clip(v + rnd_state.random() - 0.5, 0, 1) hsv = cv2.merge([h, s, v]) img = np.clip(cv2.cvtColor(hsv, cv2.COLOR_HSV2BGR), 0, 1) elif mode_type == SPTF.MODE_G: img = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY)[..., None] elif mode_type == SPTF.MODE_GGG: img = np.repeat( np.expand_dims( cv2.cvtColor(img_bgr, cv2.COLOR_BGR2GRAY), -1), (3, ), -1) elif mode_type == SPTF.MODE_M and is_face_sample: img = img_mask if not debug: if normalize_tanh: img = np.clip(img * 2.0 - 1.0, -1.0, 1.0) else: img = np.clip(img, 0.0, 1.0) if data_format == "NCHW": img = np.transpose(img, (2, 0, 1)) outputs_sample.append(img) outputs += [outputs_sample] return outputs
def MergeMaskedFace(predictor_func, predictor_input_shape, cfg, frame_info, img_bgr_uint8, img_bgr, img_face_landmarks): img_size = img_bgr.shape[1], img_bgr.shape[0] img_face_mask_a = LandmarksProcessor.get_image_hull_mask( img_bgr.shape, img_face_landmarks) if cfg.mode == 'original': if cfg.export_mask_alpha: img_bgr = np.concatenate([img_bgr, img_face_mask_a], -1) return img_bgr, img_face_mask_a out_img = img_bgr.copy() out_merging_mask = None output_size = predictor_input_shape[0] if cfg.super_resolution_mode != 0: output_size *= 4 face_mat = LandmarksProcessor.get_transform_mat(img_face_landmarks, output_size, face_type=cfg.face_type) face_output_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, output_size, face_type=cfg.face_type, scale=1.0 + 0.01 * cfg.output_face_scale) dst_face_bgr = cv2.warpAffine(img_bgr, face_mat, (output_size, output_size), flags=cv2.INTER_CUBIC) dst_face_bgr = np.clip(dst_face_bgr, 0, 1) dst_face_mask_a_0 = cv2.warpAffine(img_face_mask_a, face_mat, (output_size, output_size), flags=cv2.INTER_CUBIC) dst_face_mask_a_0 = np.clip(dst_face_mask_a_0, 0, 1) predictor_input_bgr = cv2.resize(dst_face_bgr, predictor_input_shape[0:2]) predicted = predictor_func(predictor_input_bgr) if isinstance(predicted, tuple): #merger return bgr,mask prd_face_bgr = np.clip(predicted[0], 0, 1.0) prd_face_mask_a_0 = np.clip(predicted[1], 0, 1.0) predictor_masked = True else: #merger return bgr only, using dst mask prd_face_bgr = np.clip(predicted, 0, 1.0) prd_face_mask_a_0 = cv2.resize(dst_face_mask_a_0, predictor_input_shape[0:2]) predictor_masked = False if cfg.super_resolution_mode: prd_face_bgr = cfg.superres_func(cfg.super_resolution_mode, prd_face_bgr) prd_face_bgr = np.clip(prd_face_bgr, 0, 1) if predictor_masked: prd_face_mask_a_0 = cv2.resize(prd_face_mask_a_0, (output_size, output_size), cv2.INTER_CUBIC) else: prd_face_mask_a_0 = cv2.resize(dst_face_mask_a_0, (output_size, output_size), cv2.INTER_CUBIC) if cfg.mask_mode == 2: #dst prd_face_mask_a_0 = cv2.resize(dst_face_mask_a_0, (output_size, output_size), cv2.INTER_CUBIC) elif cfg.mask_mode >= 3 and cfg.mask_mode <= 8: if cfg.mask_mode == 3 or cfg.mask_mode == 5 or cfg.mask_mode == 6: prd_face_fanseg_bgr = cv2.resize(prd_face_bgr, (cfg.fanseg_input_size, ) * 2) prd_face_fanseg_mask = cfg.fanseg_extract_func( FaceType.FULL, prd_face_fanseg_bgr) FAN_prd_face_mask_a_0 = cv2.resize(prd_face_fanseg_mask, (output_size, output_size), cv2.INTER_CUBIC) if cfg.mask_mode >= 4 and cfg.mask_mode <= 7: full_face_fanseg_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, cfg.fanseg_input_size, face_type=FaceType.FULL) dst_face_fanseg_bgr = cv2.warpAffine(img_bgr, full_face_fanseg_mat, (cfg.fanseg_input_size, ) * 2, flags=cv2.INTER_CUBIC) dst_face_fanseg_mask = cfg.fanseg_extract_func( FaceType.FULL, dst_face_fanseg_bgr) if cfg.face_type == FaceType.FULL: FAN_dst_face_mask_a_0 = cv2.resize(dst_face_fanseg_mask, (output_size, output_size), cv2.INTER_CUBIC) else: face_fanseg_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, cfg.fanseg_input_size, face_type=cfg.face_type) fanseg_rect_corner_pts = np.array( [[0, 0], [cfg.fanseg_input_size - 1, 0], [0, cfg.fanseg_input_size - 1]], dtype=np.float32) a = LandmarksProcessor.transform_points(fanseg_rect_corner_pts, face_fanseg_mat, invert=True) b = LandmarksProcessor.transform_points( a, full_face_fanseg_mat) m = cv2.getAffineTransform(b, fanseg_rect_corner_pts) FAN_dst_face_mask_a_0 = cv2.warpAffine( dst_face_fanseg_mask, m, (cfg.fanseg_input_size, ) * 2, flags=cv2.INTER_CUBIC) FAN_dst_face_mask_a_0 = cv2.resize(FAN_dst_face_mask_a_0, (output_size, output_size), cv2.INTER_CUBIC) if cfg.mask_mode == 3: #FAN-prd prd_face_mask_a_0 = FAN_prd_face_mask_a_0 elif cfg.mask_mode == 4: #FAN-dst prd_face_mask_a_0 = FAN_dst_face_mask_a_0 elif cfg.mask_mode == 5: prd_face_mask_a_0 = FAN_prd_face_mask_a_0 * FAN_dst_face_mask_a_0 elif cfg.mask_mode == 6: prd_face_mask_a_0 = prd_face_mask_a_0 * FAN_prd_face_mask_a_0 * FAN_dst_face_mask_a_0 elif cfg.mask_mode == 7: prd_face_mask_a_0 = prd_face_mask_a_0 * FAN_dst_face_mask_a_0 #elif cfg.mask_mode == 8: #FANCHQ-dst # prd_face_mask_a_0 = FANCHQ_dst_face_mask_a_0 prd_face_mask_a_0[prd_face_mask_a_0 < 0.001] = 0.0 prd_face_mask_a = prd_face_mask_a_0[..., np.newaxis] prd_face_mask_aaa = np.repeat(prd_face_mask_a, (3, ), axis=-1) img_face_mask_aaa = cv2.warpAffine(prd_face_mask_aaa, face_output_mat, img_size, np.zeros(img_bgr.shape, dtype=np.float32), flags=cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC) img_face_mask_aaa = np.clip(img_face_mask_aaa, 0.0, 1.0) img_face_mask_aaa[img_face_mask_aaa <= 0.1] = 0.0 #get rid of noise if 'raw' in cfg.mode: face_corner_pts = np.array( [[0, 0], [output_size - 1, 0], [output_size - 1, output_size - 1], [0, output_size - 1]], dtype=np.float32) square_mask = np.zeros(img_bgr.shape, dtype=np.float32) cv2.fillConvexPoly(square_mask, \ LandmarksProcessor.transform_points (face_corner_pts, face_output_mat, invert=True ).astype(np.int), \ (1,1,1) ) if cfg.mode == 'raw-rgb': out_merging_mask = square_mask if cfg.mode == 'raw-rgb' or cfg.mode == 'raw-rgb-mask': out_img = cv2.warpAffine(prd_face_bgr, face_output_mat, img_size, out_img, cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT) if cfg.mode == 'raw-rgb-mask': out_img = np.concatenate( [out_img, np.expand_dims(img_face_mask_aaa[:, :, 0], -1)], -1) out_merging_mask = square_mask elif cfg.mode == 'raw-mask-only': out_img = img_face_mask_aaa out_merging_mask = img_face_mask_aaa elif cfg.mode == 'raw-predicted-only': out_img = cv2.warpAffine(prd_face_bgr, face_output_mat, img_size, np.zeros(img_bgr.shape, dtype=np.float32), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT) out_merging_mask = square_mask out_img = np.clip(out_img, 0.0, 1.0) else: #averaging [lenx, leny, maskx, masky] by grayscale gradients of upscaled mask ar = [] for i in range(1, 10): maxregion = np.argwhere(img_face_mask_aaa > i / 10.0) if maxregion.size != 0: miny, minx = maxregion.min(axis=0)[:2] maxy, maxx = maxregion.max(axis=0)[:2] lenx = maxx - minx leny = maxy - miny if min(lenx, leny) >= 4: ar += [[lenx, leny]] if len(ar) > 0: lenx, leny = np.mean(ar, axis=0) lowest_len = min(lenx, leny) if cfg.erode_mask_modifier != 0: ero = int(lowest_len * (0.126 - lowest_len * 0.00004551365) * 0.01 * cfg.erode_mask_modifier) if ero > 0: img_face_mask_aaa = cv2.erode(img_face_mask_aaa, cv2.getStructuringElement( cv2.MORPH_ELLIPSE, (ero, ero)), iterations=1) elif ero < 0: img_face_mask_aaa = cv2.dilate(img_face_mask_aaa, cv2.getStructuringElement( cv2.MORPH_ELLIPSE, (-ero, -ero)), iterations=1) if cfg.clip_hborder_mask_per > 0: #clip hborder before blur prd_hborder_rect_mask_a = np.ones(prd_face_mask_a.shape, dtype=np.float32) prd_border_size = int(prd_hborder_rect_mask_a.shape[1] * cfg.clip_hborder_mask_per) prd_hborder_rect_mask_a[:, 0:prd_border_size, :] = 0 prd_hborder_rect_mask_a[:, -prd_border_size:, :] = 0 prd_hborder_rect_mask_a[-prd_border_size:, :, :] = 0 prd_hborder_rect_mask_a = np.expand_dims( cv2.blur(prd_hborder_rect_mask_a, (prd_border_size, prd_border_size)), -1) img_prd_hborder_rect_mask_a = cv2.warpAffine( prd_hborder_rect_mask_a, face_output_mat, img_size, np.zeros(img_bgr.shape, dtype=np.float32), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC) img_prd_hborder_rect_mask_a = np.expand_dims( img_prd_hborder_rect_mask_a, -1) img_face_mask_aaa *= img_prd_hborder_rect_mask_a img_face_mask_aaa = np.clip(img_face_mask_aaa, 0, 1.0) if cfg.blur_mask_modifier > 0: blur = int(lowest_len * 0.10 * 0.01 * cfg.blur_mask_modifier) if blur > 0: img_face_mask_aaa = cv2.blur(img_face_mask_aaa, (blur, blur)) img_face_mask_aaa = np.clip(img_face_mask_aaa, 0, 1.0) if 'seamless' not in cfg.mode and cfg.color_transfer_mode != 0: if cfg.color_transfer_mode == 1: #rct prd_face_bgr = imagelib.reinhard_color_transfer( (prd_face_bgr * 255).astype(np.uint8), (dst_face_bgr * 255).astype(np.uint8), source_mask=prd_face_mask_a, target_mask=prd_face_mask_a) prd_face_bgr = np.clip( prd_face_bgr.astype(np.float32) / 255.0, 0.0, 1.0) elif cfg.color_transfer_mode == 2: #lct prd_face_bgr = imagelib.linear_color_transfer( prd_face_bgr, dst_face_bgr) prd_face_bgr = np.clip(prd_face_bgr, 0.0, 1.0) elif cfg.color_transfer_mode == 3: #mkl prd_face_bgr = imagelib.color_transfer_mkl( prd_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 4: #mkl-m prd_face_bgr = imagelib.color_transfer_mkl( prd_face_bgr * prd_face_mask_a, dst_face_bgr * prd_face_mask_a) elif cfg.color_transfer_mode == 5: #idt prd_face_bgr = imagelib.color_transfer_idt( prd_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 6: #idt-m prd_face_bgr = imagelib.color_transfer_idt( prd_face_bgr * prd_face_mask_a, dst_face_bgr * prd_face_mask_a) elif cfg.color_transfer_mode == 7: #sot-m prd_face_bgr = imagelib.color_transfer_sot( prd_face_bgr * prd_face_mask_a, dst_face_bgr * prd_face_mask_a) prd_face_bgr = np.clip(prd_face_bgr, 0.0, 1.0) elif cfg.color_transfer_mode == 8: #mix-m prd_face_bgr = imagelib.color_transfer_mix( prd_face_bgr * prd_face_mask_a, dst_face_bgr * prd_face_mask_a) if cfg.mode == 'hist-match-bw': prd_face_bgr = cv2.cvtColor(prd_face_bgr, cv2.COLOR_BGR2GRAY) prd_face_bgr = np.repeat(np.expand_dims(prd_face_bgr, -1), (3, ), -1) if cfg.mode == 'hist-match' or cfg.mode == 'hist-match-bw': hist_mask_a = np.ones(prd_face_bgr.shape[:2] + (1, ), dtype=np.float32) if cfg.masked_hist_match: hist_mask_a *= prd_face_mask_a white = (1.0 - hist_mask_a) * np.ones( prd_face_bgr.shape[:2] + (1, ), dtype=np.float32) hist_match_1 = prd_face_bgr * hist_mask_a + white hist_match_1[hist_match_1 > 1.0] = 1.0 hist_match_2 = dst_face_bgr * hist_mask_a + white hist_match_2[hist_match_1 > 1.0] = 1.0 prd_face_bgr = imagelib.color_hist_match( hist_match_1, hist_match_2, cfg.hist_match_threshold).astype(dtype=np.float32) if cfg.mode == 'hist-match-bw': prd_face_bgr = prd_face_bgr.astype(dtype=np.float32) if 'seamless' in cfg.mode: #mask used for cv2.seamlessClone img_face_mask_a = img_face_mask_aaa[..., 0:1] img_face_seamless_mask_a = None for i in range(1, 10): a = img_face_mask_a > i / 10.0 if len(np.argwhere(a)) == 0: continue img_face_seamless_mask_a = img_face_mask_a.copy() img_face_seamless_mask_a[a] = 1.0 img_face_seamless_mask_a[img_face_seamless_mask_a <= i / 10.0] = 0.0 break out_img = cv2.warpAffine(prd_face_bgr, face_output_mat, img_size, out_img, cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT) out_img = np.clip(out_img, 0.0, 1.0) if 'seamless' in cfg.mode: try: #calc same bounding rect and center point as in cv2.seamlessClone to prevent jittering (not flickering) l, t, w, h = cv2.boundingRect( (img_face_seamless_mask_a * 255).astype(np.uint8)) s_maskx, s_masky = int(l + w / 2), int(t + h / 2) out_img = cv2.seamlessClone( (out_img * 255).astype(np.uint8), img_bgr_uint8, (img_face_seamless_mask_a * 255).astype(np.uint8), (s_maskx, s_masky), cv2.NORMAL_CLONE) out_img = out_img.astype(dtype=np.float32) / 255.0 except Exception as e: #seamlessClone may fail in some cases e_str = traceback.format_exc() if 'MemoryError' in e_str: raise Exception( "Seamless fail: " + e_str ) #reraise MemoryError in order to reprocess this data by other processes else: print("Seamless fail: " + e_str) out_img = img_bgr * (1 - img_face_mask_aaa) + (out_img * img_face_mask_aaa) out_face_bgr = cv2.warpAffine(out_img, face_mat, (output_size, output_size)) if 'seamless' in cfg.mode and cfg.color_transfer_mode != 0: if cfg.color_transfer_mode == 1: face_mask_aaa = cv2.warpAffine(img_face_mask_aaa, face_mat, (output_size, output_size)) out_face_bgr = imagelib.reinhard_color_transfer( (out_face_bgr * 255).astype(np.uint8), (dst_face_bgr * 255).astype(np.uint8), source_mask=face_mask_aaa, target_mask=face_mask_aaa) out_face_bgr = np.clip( out_face_bgr.astype(np.float32) / 255.0, 0.0, 1.0) elif cfg.color_transfer_mode == 2: #lct out_face_bgr = imagelib.linear_color_transfer( out_face_bgr, dst_face_bgr) out_face_bgr = np.clip(out_face_bgr, 0.0, 1.0) elif cfg.color_transfer_mode == 3: #mkl out_face_bgr = imagelib.color_transfer_mkl( out_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 4: #mkl-m out_face_bgr = imagelib.color_transfer_mkl( out_face_bgr * prd_face_mask_a, dst_face_bgr * prd_face_mask_a) elif cfg.color_transfer_mode == 5: #idt out_face_bgr = imagelib.color_transfer_idt( out_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 6: #idt-m out_face_bgr = imagelib.color_transfer_idt( out_face_bgr * prd_face_mask_a, dst_face_bgr * prd_face_mask_a) elif cfg.color_transfer_mode == 7: #sot-m out_face_bgr = imagelib.color_transfer_sot( out_face_bgr * prd_face_mask_a, dst_face_bgr * prd_face_mask_a) out_face_bgr = np.clip(out_face_bgr, 0.0, 1.0) elif cfg.color_transfer_mode == 8: #mix-m out_face_bgr = imagelib.color_transfer_mix( out_face_bgr * prd_face_mask_a, dst_face_bgr * prd_face_mask_a) if cfg.mode == 'seamless-hist-match': out_face_bgr = imagelib.color_hist_match( out_face_bgr, dst_face_bgr, cfg.hist_match_threshold) cfg_mp = cfg.motion_blur_power / 100.0 if cfg_mp != 0: k_size = int(frame_info.motion_power * cfg_mp) if k_size >= 1: k_size = np.clip(k_size + 1, 2, 50) if cfg.super_resolution_mode: k_size *= 2 out_face_bgr = imagelib.LinearMotionBlur( out_face_bgr, k_size, frame_info.motion_deg) if cfg.blursharpen_amount != 0: out_face_bgr = cfg.blursharpen_func(out_face_bgr, cfg.sharpen_mode, 3, cfg.blursharpen_amount) if cfg.image_denoise_power != 0: n = cfg.image_denoise_power while n > 0: img_bgr_denoised = cv2.medianBlur(img_bgr, 5) if int(n / 100) != 0: img_bgr = img_bgr_denoised else: pass_power = (n % 100) / 100.0 img_bgr = img_bgr * ( 1.0 - pass_power) + img_bgr_denoised * pass_power n = max(n - 10, 0) if cfg.bicubic_degrade_power != 0: p = 1.0 - cfg.bicubic_degrade_power / 101.0 img_bgr_downscaled = cv2.resize( img_bgr, (int(img_size[0] * p), int(img_size[1] * p)), cv2.INTER_CUBIC) img_bgr = cv2.resize(img_bgr_downscaled, img_size, cv2.INTER_CUBIC) new_out = cv2.warpAffine(out_face_bgr, face_mat, img_size, img_bgr.copy(), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT) out_img = np.clip( img_bgr * (1 - img_face_mask_aaa) + (new_out * img_face_mask_aaa), 0, 1.0) if cfg.color_degrade_power != 0: out_img_reduced = imagelib.reduce_colors(out_img, 256) if cfg.color_degrade_power == 100: out_img = out_img_reduced else: alpha = cfg.color_degrade_power / 100.0 out_img = (out_img * (1.0 - alpha) + out_img_reduced * alpha) out_merging_mask = img_face_mask_aaa return out_img, out_merging_mask[..., 0:1]
def MergeMaskedFace(predictor_func, predictor_input_shape, face_enhancer_func, xseg_256_extract_func, cfg, frame_info, img_bgr_uint8, img_bgr, img_face_landmarks): img_size = img_bgr.shape[1], img_bgr.shape[0] img_face_mask_a = LandmarksProcessor.get_image_hull_mask( img_bgr.shape, img_face_landmarks) out_img = img_bgr.copy() out_merging_mask_a = None input_size = predictor_input_shape[0] mask_subres_size = input_size * 4 output_size = input_size if cfg.super_resolution_power != 0: output_size *= 4 face_mat = LandmarksProcessor.get_transform_mat(img_face_landmarks, output_size, face_type=cfg.face_type) face_output_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, output_size, face_type=cfg.face_type, scale=1.0 + 0.01 * cfg.output_face_scale) if mask_subres_size == output_size: face_mask_output_mat = face_output_mat else: face_mask_output_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, mask_subres_size, face_type=cfg.face_type, scale=1.0 + 0.01 * cfg.output_face_scale) dst_face_bgr = cv2.warpAffine(img_bgr, face_mat, (output_size, output_size), flags=cv2.INTER_CUBIC) dst_face_bgr = np.clip(dst_face_bgr, 0, 1) dst_face_mask_a_0 = cv2.warpAffine(img_face_mask_a, face_mat, (output_size, output_size), flags=cv2.INTER_CUBIC) dst_face_mask_a_0 = np.clip(dst_face_mask_a_0, 0, 1) predictor_input_bgr = cv2.resize(dst_face_bgr, (input_size, input_size)) predicted = predictor_func(predictor_input_bgr) prd_face_bgr = np.clip(predicted[0], 0, 1.0) prd_face_mask_a_0 = np.clip(predicted[1], 0, 1.0) prd_face_dst_mask_a_0 = np.clip(predicted[2], 0, 1.0) if cfg.super_resolution_power != 0: prd_face_bgr_enhanced = face_enhancer_func(prd_face_bgr, is_tanh=True, preserve_size=False) mod = cfg.super_resolution_power / 100.0 prd_face_bgr = cv2.resize(prd_face_bgr, (output_size, output_size)) * ( 1.0 - mod) + prd_face_bgr_enhanced * mod prd_face_bgr = np.clip(prd_face_bgr, 0, 1) if cfg.super_resolution_power != 0: prd_face_mask_a_0 = cv2.resize(prd_face_mask_a_0, (output_size, output_size), cv2.INTER_CUBIC) prd_face_dst_mask_a_0 = cv2.resize(prd_face_dst_mask_a_0, (output_size, output_size), cv2.INTER_CUBIC) if cfg.mask_mode == 1: #dst wrk_face_mask_a_0 = cv2.resize(dst_face_mask_a_0, (output_size, output_size), cv2.INTER_CUBIC) elif cfg.mask_mode == 2: #learned-prd wrk_face_mask_a_0 = prd_face_mask_a_0 elif cfg.mask_mode == 3: #learned-dst wrk_face_mask_a_0 = prd_face_dst_mask_a_0 elif cfg.mask_mode == 4: #learned-prd*learned-dst wrk_face_mask_a_0 = prd_face_mask_a_0 * prd_face_dst_mask_a_0 elif cfg.mask_mode == 5: #learned-prd+learned-dst wrk_face_mask_a_0 = np.clip(prd_face_mask_a_0 + prd_face_dst_mask_a_0, 0, 1) elif cfg.mask_mode >= 6 and cfg.mask_mode <= 9: #XSeg modes if cfg.mask_mode == 6 or cfg.mask_mode == 8 or cfg.mask_mode == 9: # obtain XSeg-prd prd_face_xseg_bgr = cv2.resize(prd_face_bgr, (xseg_input_size, ) * 2, cv2.INTER_CUBIC) prd_face_xseg_mask = xseg_256_extract_func(prd_face_xseg_bgr) X_prd_face_mask_a_0 = cv2.resize(prd_face_xseg_mask, (output_size, output_size), cv2.INTER_CUBIC) if cfg.mask_mode >= 7 and cfg.mask_mode <= 9: # obtain XSeg-dst xseg_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, xseg_input_size, face_type=cfg.face_type) dst_face_xseg_bgr = cv2.warpAffine(img_bgr, xseg_mat, (xseg_input_size, ) * 2, flags=cv2.INTER_CUBIC) dst_face_xseg_mask = xseg_256_extract_func(dst_face_xseg_bgr) X_dst_face_mask_a_0 = cv2.resize(dst_face_xseg_mask, (output_size, output_size), cv2.INTER_CUBIC) if cfg.mask_mode == 6: #'XSeg-prd' wrk_face_mask_a_0 = X_prd_face_mask_a_0 elif cfg.mask_mode == 7: #'XSeg-dst' wrk_face_mask_a_0 = X_dst_face_mask_a_0 elif cfg.mask_mode == 8: #'XSeg-prd*XSeg-dst' wrk_face_mask_a_0 = X_prd_face_mask_a_0 * X_dst_face_mask_a_0 elif cfg.mask_mode == 9: #learned-prd*learned-dst*XSeg-prd*XSeg-dst wrk_face_mask_a_0 = prd_face_mask_a_0 * prd_face_dst_mask_a_0 * X_prd_face_mask_a_0 * X_dst_face_mask_a_0 wrk_face_mask_a_0[wrk_face_mask_a_0 < (1.0 / 255.0)] = 0.0 # get rid of noise # resize to mask_subres_size if wrk_face_mask_a_0.shape[0] != mask_subres_size: wrk_face_mask_a_0 = cv2.resize(wrk_face_mask_a_0, (mask_subres_size, mask_subres_size), cv2.INTER_CUBIC) # process mask in local predicted space if 'raw' not in cfg.mode: # add zero pad wrk_face_mask_a_0 = np.pad(wrk_face_mask_a_0, input_size) ero = cfg.erode_mask_modifier blur = cfg.blur_mask_modifier if ero > 0: wrk_face_mask_a_0 = cv2.erode(wrk_face_mask_a_0, cv2.getStructuringElement( cv2.MORPH_ELLIPSE, (ero, ero)), iterations=1) elif ero < 0: wrk_face_mask_a_0 = cv2.dilate(wrk_face_mask_a_0, cv2.getStructuringElement( cv2.MORPH_ELLIPSE, (-ero, -ero)), iterations=1) # clip eroded/dilated mask in actual predict area # pad with half blur size in order to accuratelly fade to zero at the boundary clip_size = input_size + blur // 2 wrk_face_mask_a_0[:clip_size, :] = 0 wrk_face_mask_a_0[-clip_size:, :] = 0 wrk_face_mask_a_0[:, :clip_size] = 0 wrk_face_mask_a_0[:, -clip_size:] = 0 if blur > 0: blur = blur + (1 - blur % 2) wrk_face_mask_a_0 = cv2.GaussianBlur(wrk_face_mask_a_0, (blur, blur), 0) wrk_face_mask_a_0 = wrk_face_mask_a_0[input_size:-input_size, input_size:-input_size] wrk_face_mask_a_0 = np.clip(wrk_face_mask_a_0, 0, 1) img_face_mask_a = cv2.warpAffine(wrk_face_mask_a_0, face_mask_output_mat, img_size, np.zeros(img_bgr.shape[0:2], dtype=np.float32), flags=cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC)[..., None] img_face_mask_a = np.clip(img_face_mask_a, 0.0, 1.0) img_face_mask_a[img_face_mask_a < (1.0 / 255.0)] = 0.0 # get rid of noise if wrk_face_mask_a_0.shape[0] != output_size: wrk_face_mask_a_0 = cv2.resize(wrk_face_mask_a_0, (output_size, output_size), cv2.INTER_CUBIC) wrk_face_mask_a = wrk_face_mask_a_0[..., None] wrk_face_mask_area_a = wrk_face_mask_a.copy() wrk_face_mask_area_a[wrk_face_mask_area_a > 0] = 1.0 if cfg.mode == 'original': return img_bgr, img_face_mask_a elif 'raw' in cfg.mode: if cfg.mode == 'raw-rgb': out_img = cv2.warpAffine(prd_face_bgr, face_output_mat, img_size, out_img, cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT) out_merging_mask_a = img_face_mask_a elif cfg.mode == 'raw-predict': out_img = prd_face_bgr out_merging_mask_a = wrk_face_mask_a out_img = np.clip(out_img, 0.0, 1.0) else: #averaging [lenx, leny, maskx, masky] by grayscale gradients of upscaled mask ar = [] for i in range(1, 10): maxregion = np.argwhere(img_face_mask_a > i / 10.0) if maxregion.size != 0: miny, minx = maxregion.min(axis=0)[:2] maxy, maxx = maxregion.max(axis=0)[:2] lenx = maxx - minx leny = maxy - miny if min(lenx, leny) >= 4: ar += [[lenx, leny]] if len(ar) > 0: if 'seamless' not in cfg.mode and cfg.color_transfer_mode != 0: if cfg.color_transfer_mode == 1: #rct prd_face_bgr = imagelib.reinhard_color_transfer( np.clip(prd_face_bgr * wrk_face_mask_area_a * 255, 0, 255).astype(np.uint8), np.clip(dst_face_bgr * wrk_face_mask_area_a * 255, 0, 255).astype(np.uint8), ) prd_face_bgr = np.clip( prd_face_bgr.astype(np.float32) / 255.0, 0.0, 1.0) elif cfg.color_transfer_mode == 2: #lct prd_face_bgr = imagelib.linear_color_transfer( prd_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 3: #mkl prd_face_bgr = imagelib.color_transfer_mkl( prd_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 4: #mkl-m prd_face_bgr = imagelib.color_transfer_mkl( prd_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a) elif cfg.color_transfer_mode == 5: #idt prd_face_bgr = imagelib.color_transfer_idt( prd_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 6: #idt-m prd_face_bgr = imagelib.color_transfer_idt( prd_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a) elif cfg.color_transfer_mode == 7: #sot-m prd_face_bgr = imagelib.color_transfer_sot( prd_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a, steps=10, batch_size=30) prd_face_bgr = np.clip(prd_face_bgr, 0.0, 1.0) elif cfg.color_transfer_mode == 8: #mix-m prd_face_bgr = imagelib.color_transfer_mix( prd_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a) if cfg.mode == 'hist-match': hist_mask_a = np.ones(prd_face_bgr.shape[:2] + (1, ), dtype=np.float32) if cfg.masked_hist_match: hist_mask_a *= wrk_face_mask_area_a white = (1.0 - hist_mask_a) * np.ones( prd_face_bgr.shape[:2] + (1, ), dtype=np.float32) hist_match_1 = prd_face_bgr * hist_mask_a + white hist_match_1[hist_match_1 > 1.0] = 1.0 hist_match_2 = dst_face_bgr * hist_mask_a + white hist_match_2[hist_match_1 > 1.0] = 1.0 prd_face_bgr = imagelib.color_hist_match( hist_match_1, hist_match_2, cfg.hist_match_threshold).astype(dtype=np.float32) if 'seamless' in cfg.mode: #mask used for cv2.seamlessClone img_face_seamless_mask_a = None for i in range(1, 10): a = img_face_mask_a > i / 10.0 if len(np.argwhere(a)) == 0: continue img_face_seamless_mask_a = img_face_mask_a.copy() img_face_seamless_mask_a[a] = 1.0 img_face_seamless_mask_a[img_face_seamless_mask_a <= i / 10.0] = 0.0 break out_img = cv2.warpAffine(prd_face_bgr, face_output_mat, img_size, out_img, cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT) out_img = np.clip(out_img, 0.0, 1.0) if 'seamless' in cfg.mode: try: #calc same bounding rect and center point as in cv2.seamlessClone to prevent jittering (not flickering) l, t, w, h = cv2.boundingRect( (img_face_seamless_mask_a * 255).astype(np.uint8)) s_maskx, s_masky = int(l + w / 2), int(t + h / 2) out_img = cv2.seamlessClone( (out_img * 255).astype(np.uint8), img_bgr_uint8, (img_face_seamless_mask_a * 255).astype(np.uint8), (s_maskx, s_masky), cv2.NORMAL_CLONE) out_img = out_img.astype(dtype=np.float32) / 255.0 except Exception as e: #seamlessClone may fail in some cases e_str = traceback.format_exc() if 'MemoryError' in e_str: raise Exception( "Seamless fail: " + e_str ) #reraise MemoryError in order to reprocess this data by other processes else: print("Seamless fail: " + e_str) cfg_mp = 0.3 #todo cfg.motion_blur_power / 100.0 ### shrink_res = output_size #512 shrink_prd_face_dst_mask_a_0 = cv2.resize(prd_face_dst_mask_a_0, (shrink_res, shrink_res), cv2.INTER_CUBIC) shrink_blur_size = (shrink_res // 32) + 1 shrink_blur_size += (1 - shrink_blur_size % 2) # Feather the mask shrink_prd_face_dst_mask_a_0 = cv2.GaussianBlur( shrink_prd_face_dst_mask_a_0, (shrink_blur_size, shrink_blur_size), 0) shrink_prd_face_dst_mask_a_0[ shrink_prd_face_dst_mask_a_0 < 0.5] = 0.0 shrink_prd_face_dst_mask_a_0[ shrink_prd_face_dst_mask_a_0 >= 0.5] = 1.0 cnts = cv2.findContours( shrink_prd_face_dst_mask_a_0.astype(np.uint8), cv2.RETR_LIST, cv2.CHAIN_APPROX_TC89_KCOS) # Get the largest found contour cnt = sorted(cnts[0], key=cv2.contourArea, reverse=True)[0].squeeze() l, t = cnt.min(0) r, b = cnt.max(0) min_dist_to_edge = min(l, t, r, b) center = np.mean(cnt, 0) cnt2 = cnt.copy().astype(np.float32) cnt2_c = center - cnt2 cnt2_len = npla.norm(cnt2_c, axis=1, keepdims=True) cnt2_vec = cnt2_c / cnt2_len # Anchor perimeter pts_count = shrink_res // 2 h = shrink_res w = shrink_res perim_pts = np.concatenate( (np.concatenate([ np.arange(0, w + w / pts_count, w / pts_count)[..., None], np.array([[0]] * (pts_count + 1)) ], axis=-1), np.concatenate([ np.arange(0, w + w / pts_count, w / pts_count)[..., None], np.array([[h]] * (pts_count + 1)) ], axis=-1), np.concatenate([ np.array([[0]] * (pts_count + 1)), np.arange(0, h + h / pts_count, h / pts_count)[..., None] ], axis=-1), np.concatenate([ np.array([[w]] * (pts_count + 1)), np.arange(0, h + h / pts_count, h / pts_count)[..., None] ], axis=-1)), 0).astype(np.int32) cnt2 += cnt2_vec * cnt2_len * cfg_mp #todo cnt2 = cnt2.astype(np.int32) cnt2 = np.concatenate((cnt2, perim_pts), 0) cnt = np.concatenate((cnt, perim_pts), 0) shrink_face_mat = LandmarksProcessor.get_transform_mat( img_face_landmarks, shrink_res, face_type=cfg.face_type) #todo check face type shrink_dst_face_bgr = cv2.warpAffine(img_bgr, shrink_face_mat, (shrink_res, shrink_res), flags=cv2.INTER_CUBIC) shrinked_dst_face_bgr = mls_rigid_deformation_inv( shrink_dst_face_bgr, cnt, cnt2) new_img_bgr = cv2.warpAffine( shrinked_dst_face_bgr, shrink_face_mat, img_size, img_bgr.copy(), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT) shrink_ero_size = int(min_dist_to_edge * 0.9) #todo shrink_ero_size += (1 - shrink_ero_size % 2) shrink_blur_size = int(shrink_ero_size * 1.5) shrink_blur_size += (1 - shrink_blur_size % 2) if shrink_ero_size != 0: shrink_prd_face_dst_mask_a_0_before = shrink_prd_face_dst_mask_a_0.copy( ) shrink_prd_face_dst_mask_a_0 = cv2.dilate( shrink_prd_face_dst_mask_a_0, cv2.getStructuringElement( cv2.MORPH_ELLIPSE, (shrink_ero_size, shrink_ero_size)), iterations=1) shrink_prd_face_dst_mask_a_0 = cv2.GaussianBlur( shrink_prd_face_dst_mask_a_0, (shrink_blur_size, shrink_blur_size), 0) #while True: # cv2.imshow("", (shrink_prd_face_dst_mask_a_0_before*255).astype(np.uint8) ) # cv2.waitKey(0) # cv2.imshow("", (shrink_prd_face_dst_mask_a_0*255).astype(np.uint8) ) # cv2.waitKey(0) shrink_img_mask = cv2.warpAffine( shrink_prd_face_dst_mask_a_0, shrink_face_mat, img_size, img_bgr.copy(), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT) shrink_img_mask_a = shrink_img_mask[..., None] new_img_bgr = img_bgr * (1 - shrink_img_mask_a) + ( new_img_bgr * shrink_img_mask_a) #cv2.imshow("", (shrink_dst_face_bgr*255).astype(np.uint8) ) #cv2.waitKey(0) #cv2.imshow("", (shrinked_dst_face_bgr*255).astype(np.uint8) ) #cv2.waitKey(0) while True: cv2.imshow("", (img_bgr * 255).astype(np.uint8)) cv2.waitKey(0) cv2.imshow("", (new_img_bgr * 255).astype(np.uint8)) cv2.waitKey(0) #cv2.imshow("", (shrink_img_mask*255).astype(np.uint8) ) #cv2.waitKey(0) ### out_img = img_bgr * (1 - img_face_mask_a) + (out_img * img_face_mask_a) if ('seamless' in cfg.mode and cfg.color_transfer_mode != 0) or \ cfg.mode == 'seamless-hist-match' or \ cfg_mp != 0 or \ cfg.blursharpen_amount != 0 or \ cfg.image_denoise_power != 0 or \ cfg.bicubic_degrade_power != 0: out_face_bgr = cv2.warpAffine(out_img, face_mat, (output_size, output_size), flags=cv2.INTER_CUBIC) if 'seamless' in cfg.mode and cfg.color_transfer_mode != 0: if cfg.color_transfer_mode == 1: out_face_bgr = imagelib.reinhard_color_transfer( np.clip(out_face_bgr * wrk_face_mask_area_a * 255, 0, 255).astype(np.uint8), np.clip(dst_face_bgr * wrk_face_mask_area_a * 255, 0, 255).astype(np.uint8)) out_face_bgr = np.clip( out_face_bgr.astype(np.float32) / 255.0, 0.0, 1.0) elif cfg.color_transfer_mode == 2: #lct out_face_bgr = imagelib.linear_color_transfer( out_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 3: #mkl out_face_bgr = imagelib.color_transfer_mkl( out_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 4: #mkl-m out_face_bgr = imagelib.color_transfer_mkl( out_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a) elif cfg.color_transfer_mode == 5: #idt out_face_bgr = imagelib.color_transfer_idt( out_face_bgr, dst_face_bgr) elif cfg.color_transfer_mode == 6: #idt-m out_face_bgr = imagelib.color_transfer_idt( out_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a) elif cfg.color_transfer_mode == 7: #sot-m out_face_bgr = imagelib.color_transfer_sot( out_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a, steps=10, batch_size=30) out_face_bgr = np.clip(out_face_bgr, 0.0, 1.0) elif cfg.color_transfer_mode == 8: #mix-m out_face_bgr = imagelib.color_transfer_mix( out_face_bgr * wrk_face_mask_area_a, dst_face_bgr * wrk_face_mask_area_a) if cfg.mode == 'seamless-hist-match': out_face_bgr = imagelib.color_hist_match( out_face_bgr, dst_face_bgr, cfg.hist_match_threshold) if cfg_mp != 0: k_size = int(frame_info.motion_power * cfg_mp) if k_size >= 1: k_size = np.clip(k_size + 1, 2, 50) if cfg.super_resolution_power != 0: k_size *= 2 out_face_bgr = imagelib.LinearMotionBlur( out_face_bgr, k_size, frame_info.motion_deg) if cfg.blursharpen_amount != 0: out_face_bgr = imagelib.blursharpen( out_face_bgr, cfg.sharpen_mode, 3, cfg.blursharpen_amount) if cfg.image_denoise_power != 0: n = cfg.image_denoise_power while n > 0: img_bgr_denoised = cv2.medianBlur(img_bgr, 5) if int(n / 100) != 0: img_bgr = img_bgr_denoised else: pass_power = (n % 100) / 100.0 img_bgr = img_bgr * ( 1.0 - pass_power) + img_bgr_denoised * pass_power n = max(n - 10, 0) if cfg.bicubic_degrade_power != 0: p = 1.0 - cfg.bicubic_degrade_power / 101.0 img_bgr_downscaled = cv2.resize( img_bgr, (int(img_size[0] * p), int(img_size[1] * p)), cv2.INTER_CUBIC) img_bgr = cv2.resize(img_bgr_downscaled, img_size, cv2.INTER_CUBIC) new_out = cv2.warpAffine( out_face_bgr, face_mat, img_size, img_bgr.copy(), cv2.WARP_INVERSE_MAP | cv2.INTER_CUBIC, cv2.BORDER_TRANSPARENT) out_img = np.clip( img_bgr * (1 - img_face_mask_a) + (new_out * img_face_mask_a), 0, 1.0) if cfg.color_degrade_power != 0: out_img_reduced = imagelib.reduce_colors(out_img, 256) if cfg.color_degrade_power == 100: out_img = out_img_reduced else: alpha = cfg.color_degrade_power / 100.0 out_img = (out_img * (1.0 - alpha) + out_img_reduced * alpha) out_merging_mask_a = img_face_mask_a return out_img, out_merging_mask_a