def test_save_obj(self):
vertices, faces = neural_renderer.load_obj('./tests/data/teapot.obj')
neural_renderer.save_obj('./tests/data/teapot2.obj', vertices, faces)
vertices2, faces2 = neural_renderer.load_obj('./tests/data/teapot.obj')
os.remove('./tests/data/teapot2.obj')
assert np.allclose(vertices, vertices2)
assert np.allclose(faces, faces2)
def test_texture(self):
position, rotation = position_rotation_from_angles(2, 15, 30)
camera = nr.Camera(position=position, rotation=rotation)
renderer = nr.Renderer(camera=camera)
vertices, faces, textures = nr.load_obj(os.path.join(
data_dir, '1cde62b063e14777c9152a706245d48/model.obj'),
load_texture=True)
images = renderer(vertices[None, :, :], faces[None, :, :],
textures[None, :, :, :, :, :]).permute(
0, 2, 3, 1).detach().cpu().numpy()
image = (images[0] * 255).astype(np.uint8)
imsave(os.path.join(data_dir, 'car.png'), image)
vertices, faces, textures = nr.load_obj(os.path.join(
data_dir, '4e49873292196f02574b5684eaec43e9/model.obj'),
load_texture=True,
texture_size=16)
position, rotation = position_rotation_from_angles(2, 15, -90)
renderer.camera.position = position
renderer.camera.rotation = rotation
images = renderer(vertices[None, :, :], faces[None, :, :],
textures[None, :, :, :, :, :]).permute(
0, 2, 3, 1).detach().cpu().numpy()
image = (images[0] * 255).astype(np.uint8)
imsave(os.path.join(data_dir, 'display.png'), image)
def test_texture(self):
renderer = neural_renderer.Renderer()
vertices, faces, textures = neural_renderer.load_obj(
'./tests/data/1cde62b063e14777c9152a706245d48/model.obj',
load_texture=True)
vertices = chainer.cuda.to_gpu(vertices)
faces = chainer.cuda.to_gpu(faces)
textures = chainer.cuda.to_gpu(textures)
renderer.eye = neural_renderer.get_points_from_angles(2, 15, 30)
images = renderer.render(vertices[None, :, :], faces[None, :, :],
textures[None, :, :, :, :, :]).data.get()
scipy.misc.imsave('./tests/data/car.png',
scipy.misc.toimage(images[0]))
vertices, faces, textures = neural_renderer.load_obj(
'./tests/data/4e49873292196f02574b5684eaec43e9/model.obj',
load_texture=True,
texture_size=16)
vertices = chainer.cuda.to_gpu(vertices)
faces = chainer.cuda.to_gpu(faces)
textures = chainer.cuda.to_gpu(textures)
renderer.eye = neural_renderer.get_points_from_angles(2, 15, -90)
images = renderer.render(vertices[None, :, :], faces[None, :, :],
textures[None, :, :, :, :, :]).data.get()
scipy.misc.imsave('./tests/data/display.png',
scipy.misc.toimage(images[0]))
def test_texture(self):
renderer = nr.Renderer(camera_mode='look_at')
vertices, faces, textures = nr.load_obj(os.path.join(
data_dir, '1cde62b063e14777c9152a706245d48/model.obj'),
load_texture=True)
renderer.eye = nr.get_points_from_angles(2, 15, 30)
images, depth, silhouette = renderer.render(
vertices[None, :, :], faces[None, :, :],
textures[None, :, :, :, :, :])
images = images.permute(0, 2, 3, 1).detach().cpu().numpy()
silhouette = silhouette.detach().cpu().numpy()
depth = depth.detach().cpu().numpy()
imsave(os.path.join(data_dir, 'car.png'), images[0])
cv2.imshow("r", images[0, :, :, ::-1])
cv2.imshow("d", ColorizeDepth(depth[0], 1.5, 2.5))
cv2.imshow("s", silhouette[0])
cv2.waitKey()
vertices, faces, textures = nr.load_obj(os.path.join(
data_dir, '4e49873292196f02574b5684eaec43e9/model.obj'),
load_texture=True,
texture_size=16)
renderer.eye = nr.get_points_from_angles(2, 15, -90)
images, _, _ = renderer.render(vertices[None, :, :], faces[None, :, :],
textures[None, :, :, :, :, :])
images = images.permute(0, 2, 3, 1).detach().cpu().numpy()
imsave(os.path.join(data_dir, 'display.png'), images[0])
def test_save_obj(self):
vertices, faces = neural_renderer.load_obj('./tests/data/teapot.obj')
neural_renderer.save_obj('./tests/data/teapot2.obj', vertices, faces)
vertices2, faces2 = neural_renderer.load_obj('./tests/data/teapot.obj')
os.remove('./tests/data/teapot2.obj')
assert np.allclose(vertices, vertices2)
assert np.allclose(faces, faces2)
def test_save_obj(self):
teapot = os.path.join(data_dir, 'teapot.obj')
teapot2 = os.path.join(data_dir, 'teapot2.obj')
vertices, faces = nr.load_obj(teapot)
nr.save_obj(teapot2, vertices, faces)
vertices2, faces2 = nr.load_obj(teapot2)
os.remove(teapot2)
assert torch.allclose(vertices, vertices2)
assert torch.allclose(faces, faces2)
def __init__(self, render_type, n_channel):
super().__init__()
primitive_type = render_type
self.n_channel = n_channel
if primitive_type == 'sphere':
v, f = nr.load_obj('controllable_gan/templates/sphere_114.obj')
elif primitive_type == 'cuboid':
v, f = nr.load_obj('controllable_gan/templates/cube.obj', False)
else:
raise AttributeError
self.n_latent = 128
self.v = v
self.f = f
def test_tetrahedron(self):
vertices_ref = np.array(
[[1., 0., 0.], [0., 1., 0.], [0., 0., 1.], [0., 0., 0.]],
'float32')
faces_ref = np.array([[1, 3, 2], [3, 1, 0], [2, 0, 1], [0, 2, 3]],
'int32')
obj_file = os.path.join(data_dir, 'tetrahedron.obj')
vertices, faces = nr.load_obj(obj_file, False)
assert (np.allclose(vertices_ref, vertices))
assert (np.allclose(faces_ref, faces))
vertices, faces = nr.load_obj(obj_file, True)
assert (np.allclose(vertices_ref * 2 - 1.0, vertices))
assert (np.allclose(faces_ref, faces))
def test_tetrahedron(self):
vertices_ref = np.array(
[[1., 0., 0.], [0., 1., 0.], [0., 0., 1.], [0., 0., 0.]],
'float32')
faces_ref = np.array([[1, 3, 2], [3, 1, 0], [2, 0, 1], [0, 2, 3]],
'int32')
vertices, faces = neural_renderer.load_obj(
'./tests/data/tetrahedron.obj', False)
assert (np.allclose(vertices_ref, vertices))
assert (np.allclose(faces_ref, faces))
vertices, faces = neural_renderer.load_obj(
'./tests/data/tetrahedron.obj', True)
assert (np.allclose(vertices_ref * 2 - 1.0, vertices))
assert (np.allclose(faces_ref, faces))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-i', '--filename_input', type=str, default=os.path.join(data_dir, 'teapot.obj'))
parser.add_argument('-o', '--filename_output', type=str, default=os.path.join(data_dir, 'example1.gif'))
parser.add_argument('-g', '--gpu', type=int, default=0)
args = parser.parse_args()
# other settings
camera_distance = 2.732
elevation = 30
texture_size = 2
# load .obj
vertices, faces = nr.load_obj(args.filename_input)
vertices = vertices[None, :, :] # [num_vertices, XYZ] -> [batch_size=1, num_vertices, XYZ]
faces = faces[None, :, :] # [num_faces, 3] -> [batch_size=1, num_faces, 3]
# create texture [batch_size=1, num_faces, texture_size, texture_size, texture_size, RGB]
textures = torch.ones(1, faces.shape[1], texture_size, texture_size, texture_size, 3, dtype=torch.float32).cuda()
# to gpu
# create renderer
renderer = nr.Renderer(camera_mode='look_at')
# draw object
loop = tqdm.tqdm(range(0, 360, 4))
writer = imageio.get_writer(args.filename_output, mode='I')
for num, azimuth in enumerate(loop):
loop.set_description('Drawing')
renderer.eye = nr.get_points_from_angles(camera_distance, elevation, azimuth)
images = renderer(vertices, faces, textures) # [batch_size, RGB, image_size, image_size]
image = images.detach().cpu().numpy()[0].transpose((1, 2, 0)) # [image_size, image_size, RGB]
writer.append_data((255*image).astype(np.uint8))
writer.close()
def __init__(self, filename_obj, filename_ref):
super(Model, self).__init__()
vertices, faces = nr.load_obj(filename_obj)
self.register_buffer('vertices', vertices[None, :, :])
self.register_buffer('faces', faces[None, :, :])
# create textures
texture_size = 4
textures = torch.zeros(1,
self.faces.shape[1],
texture_size,
texture_size,
texture_size,
3,
dtype=torch.float32)
self.textures = nn.Parameter(textures)
# load reference image
image_ref = torch.from_numpy(
imread(filename_ref).astype('float32') / 255.).permute(2, 0,
1)[None, ::]
self.register_buffer('image_ref', image_ref)
# setup renderer
renderer = nr.Renderer(camera_mode='look_at')
renderer.perspective = False
renderer.light_intensity_directional = 0.0
renderer.light_intensity_ambient = 1.0
self.renderer = renderer
def __init__(self,
dim_in=512,
scaling=1.,
filename_obj='./data/obj/sphere_642.obj'):
super(BasicShapeDecoder, self).__init__()
with self.init_scope():
self.vertices_base, self.faces = neural_renderer.load_obj(
filename_obj)
self.num_vertices = self.vertices_base.shape[0]
self.num_faces = self.faces.shape[0]
self.obj_scale = 0.5
self.object_size = 1.0
self.scaling = scaling
dim_hidden = [4096, 4096]
init = chainer.initializers.HeNormal()
self.linear1 = cl.Linear(dim_in, dim_hidden[0], initialW=init)
self.linear2 = cl.Linear(dim_hidden[0],
dim_hidden[1],
initialW=init)
self.linear_bias = cl.Linear(dim_hidden[1],
self.num_vertices * 3,
initialW=init)
self.laplacian = get_graph_laplacian(self.faces, self.num_vertices)
def __init__(self,
dim_in=512,
scaling=1.,
filename_obj='./data/obj/sphere_642.obj'):
super(BasicSymmetricShapeDecoder, self).__init__()
with self.init_scope():
self.vertices_base, self.faces = neural_renderer.load_obj(
filename_obj)
self.num_vertices = self.vertices_base.shape[0]
self.num_faces = self.faces.shape[0]
self.obj_scale = 0.5
self.object_size = 1.0
self.scaling = scaling
self.vertices_base, self.vertices_matrix = self.compute_vertices_matrix(
) # [642 * 3, 337 * 3]
dim_out = self.vertices_matrix.shape[1]
dim_hidden = [4096, 4096]
init = chainer.initializers.HeNormal()
self.linear1 = cl.Linear(dim_in, dim_hidden[0], initialW=init)
self.linear2 = cl.Linear(dim_hidden[0],
dim_hidden[1],
initialW=init)
self.linear_bias = cl.Linear(dim_hidden[1], dim_out, initialW=init)
self.laplacian = get_graph_laplacian(self.faces, self.num_vertices)
self.degrees = self.xp.histogram(
self.faces,
self.xp.arange(self.num_vertices + 1))[0].astype('int32')
def stest_forward_case2(self):
data = [[
'./tests/data/4e49873292196f02574b5684eaec43e9/model.obj',
neural_renderer.get_points_from_angles(2.5, 10, -90),
'./tests/data/4e49873292196f02574b5684eaec43e9.png',
],
[
'./tests/data/1cde62b063e14777c9152a706245d48/model.obj',
neural_renderer.get_points_from_angles(2.5, 10, 60),
'./tests/data/1cde62b063e14777c9152a706245d48.png',
]]
renderer = neural_renderer.Renderer()
renderer.draw_backside = False
for i, (filename, viewpoint, reference) in enumerate(data):
renderer.viewpoints = viewpoint
ref = neural_renderer.imread(reference)
vertices, faces, vertices_t, faces_t, textures = neural_renderer.load_obj(
filename, load_textures=True)
vertices, faces, vertices_t, faces_t, textures = neural_renderer.to_gpu(
(vertices[None, :, :], faces, vertices_t[None, :, :], faces_t,
textures[None, :, :, :]))
images = renderer.render(vertices, faces, vertices_t, faces_t,
textures).data
image = images[0].transpose((1, 2, 0))
# imageio.toimage(image.get(), cmin=0, cmax=1).save(reference)
chainer.testing.assert_allclose(ref, image, atol=1e-2)
def fromobj(cls, filename_obj, normalization=True, load_texture=False, texture_size=4):
'''
Create a Mesh object from a .obj file
'''
if load_texture:
vertices, faces, textures = nr.load_obj(filename_obj,
normalization=normalization,
texture_size=texture_size,
load_texture=True)
else:
vertices, faces = nr.load_obj(filename_obj,
normalization=normalization,
texture_size=texture_size,
load_texture=False)
textures = None
return cls(vertices, faces, textures, texture_size)
def __init__(self, filename_obj, filename_ref):
super(Model, self).__init__()
# load .obj
vertices, faces = nr.load_obj(filename_obj)
self.vertices = nn.Parameter(vertices[None, :, :])
self.register_buffer('faces', faces[None, :, :])
# create textures
texture_size = 2
textures = torch.ones(1,
self.faces.shape[1],
texture_size,
texture_size,
texture_size,
3,
dtype=torch.float32)
self.register_buffer('textures', textures)
# load reference image
image_ref = torch.from_numpy(
imread(filename_ref).astype(np.float32).mean(-1) / 255.)[None, ::]
self.register_buffer('image_ref', image_ref)
# setup renderer
renderer = nr.Renderer(camera_mode='look_at')
self.renderer = renderer
def exec_main():
obj_file = 'birds3d/external/neural_renderer/examples/data/teapot.obj'
vertices, faces = neural_renderer.load_obj(obj_file)
renderer = NMR()
renderer.to_gpu(device=0)
masks = renderer.forward_mask(vertices[None, :, :], faces[None, :, :])
print(np.sum(masks))
print(masks.shape)
grad_masks = masks * 0 + 1
vert_grad = renderer.backward_mask(grad_masks)
print(np.sum(vert_grad))
print(vert_grad.shape)
# Torch API
mask_renderer = NeuralRenderer()
vertices_var = torch.autograd.Variable(torch.from_numpy(
vertices[None, :, :]).cuda(device=0),
requires_grad=True)
faces_var = torch.autograd.Variable(
torch.from_numpy(faces[None, :, :]).cuda(device=0))
for ix in range(100):
masks_torch = mask_renderer.forward(vertices_var, faces_var)
vertices_var.grad = None
masks_torch.backward(torch.from_numpy(grad_masks).cuda(device=0))
print(torch.sum(masks_torch))
print(masks_torch.shape)
print(torch.sum(vertices_var.grad))
def __init__(self, filename_obj, filename_ref=None):
super(Model, self).__init__()
with self.init_scope():
# load .obj
vertices, faces = neural_renderer.load_obj(filename_obj)
self.vertices = vertices[None, :, :]
self.faces = faces[None, :, :]
# create textures
texture_size = 2
textures = np.ones((1, self.faces.shape[1], texture_size, texture_size, texture_size, 3), 'float32')
self.textures = textures
# load reference image
if filename_ref is not None:
self.image_ref = (scipy.misc.imread(filename_ref).max(-1) != 0).astype('float32')
else:
self.image_ref = None
# camera parameters
self.camera_position = chainer.Parameter(np.array([6, 10, -14], 'float32'))
# setup renderer
renderer = neural_renderer.Renderer()
renderer.eye = self.camera_position
self.renderer = renderer
def __init__(self, filename_obj, filename_ref):
super(Model, self).__init__()
with self.init_scope():
# load .obj
vertices, faces = neural_renderer.load_obj(filename_obj)
self.vertices = vertices[None, :, :]
self.faces = faces[None, :, :]
# create textures
texture_size = 4
textures = np.zeros((1, self.faces.shape[1], texture_size,
texture_size, texture_size, 3), 'float32')
self.textures = chainer.Parameter(textures)
# load reference image
self.image_ref = scipy.misc.imread(filename_ref).astype(
'float32') / 255.
# setup renderer
renderer = neural_renderer.Renderer()
renderer.perspective = False
renderer.light_intensity_directional = 0.0
renderer.light_intensity_ambient = 1.0
self.renderer = renderer
def buffer_all(self):
# if preset_uv_path:
# self.v_attr, self.f_attr = nr.load_obj(cur_obj_fp, normalization = False)
if self.cfg.DATASET_FVV.PRELOAD_MESHS:
print(" Buffering meshs...")
self.objs = {}
for keep_idx in self.keep_idxs:
frame_idx = self.frame_idxs[keep_idx]
if frame_idx in self.objs:
continue
cur_obj_fp = self.cfg.DATASET_FVV.MESH_DIR%(frame_idx)
obj_data = {}
obj_data['v_attr'] , obj_data['f_attr'] = nr.load_obj(cur_obj_fp, normalization = False, use_cuda = False)
self.objs[frame_idx] = obj_data
if self.cfg.VERBOSE:
print(' Loading mesh: ' + str(int(frame_idx)) + ' ' + cur_obj_fp)
if self.cfg.DATASET_FVV.PRELOAD_VIEWS:
# Buffer files
print("Buffering files...")
self.views_all = []
for i in range(self.__len__()):
if not i % 50:
print('Data', i)
self.views_all.append(self.read_view(i))
def __init__(self, filename_obj, filename_ref):
super(Model, self).__init__()
with self.init_scope():
# load .obj
vertices, faces = neural_renderer.load_obj(filename_obj)
self.vertices = chainer.Parameter(vertices[None, :, :])
self.faces = faces[None, :, :]
# create textures
texture_size = 2
textures = np.ones((1, self.faces.shape[1], texture_size,
texture_size, texture_size, 3), 'float32')
self.textures = textures
# load reference image
#self.image_ref = scipy.misc.imread(filename_ref).astype('float32').mean(-1) / 255.
image_ref = scipy.misc.imread(filename_ref).astype('float32').mean(
-1) / 255.
h = image_ref.shape[0]
w = image_ref.shape[1]
hcrop = wcrop = self.image_size = 256 #np.min(image_ref.shape[:1])
top = int(math.floor((h - hcrop) / 2.0))
bottom = int(math.ceil((h + hcrop) / 2.0))
left = int(math.floor((w - wcrop) / 2.0))
right = int(math.ceil((w + wcrop) / 2.0))
if len(image_ref.shape) > 2:
self.image_ref = image_ref[top:bottom, left:right, :]
else:
self.image_ref = image_ref[top:bottom, left:right]
# setup renderer
renderer = neural_renderer.Renderer()
self.renderer = renderer
def __init__(self, filename_obj, filename_ref=None):
super(Model, self).__init__()
# load .obj
vertices, faces = nr.load_obj(filename_obj)
self.register_buffer('vertices', vertices[None, :, :])
self.register_buffer('faces', faces[None, :, :])
# create textures
texture_size = 2
textures = torch.ones(1,
self.faces.shape[1],
texture_size,
texture_size,
texture_size,
3,
dtype=torch.float32)
self.register_buffer('textures', textures)
# load reference image
image_ref = torch.from_numpy(
(imread(filename_ref).max(-1) != 0).astype(np.float32))
self.register_buffer('image_ref', image_ref)
# camera parameters
self.camera_position = nn.Parameter(
torch.from_numpy(np.array([6, 10, -14], dtype=np.float32)))
# setup renderer
renderer = nr.Renderer(camera_mode='look_at')
renderer.eye = self.camera_position
self.renderer = renderer
def __init__(self,
filename_obj,
dim_in=512,
centroid_scale=0.1,
bias_scale=1.0,
centroid_lr=0.1,
bias_lr=1.0):
super(Decoder, self).__init__()
with self.init_scope():
self.vertices_base, self.faces = neural_renderer.load_obj(
filename_obj)
self.num_vertices = self.vertices_base.shape[0]
self.num_faces = self.faces.shape[0]
self.centroid_scale = centroid_scale
self.bias_scale = bias_scale
self.obj_scale = 0.5
dim = 1024
dim_hidden = [dim, dim * 2]
self.linear1 = cl.Linear(dim_in, dim_hidden[0])
self.linear2 = cl.Linear(dim_hidden[0], dim_hidden[1])
self.linear_centroids = cl.Linear(dim_hidden[1], 3)
self.linear_bias = cl.Linear(dim_hidden[1], self.num_vertices * 3)
self.linear_centroids.W.lr = centroid_lr
self.linear_centroids.b.lr = centroid_lr
self.linear_bias.W.lr = bias_lr
self.linear_bias.b.lr = bias_lr
def __init__(self, filename_obj, filename_ref=None):
super(Model, self).__init__()
with self.init_scope():
# load .obj
vertices, faces = neural_renderer.load_obj(filename_obj)
self.vertices = vertices[None, :, :]
self.faces = faces[None, :, :]
# create textures
texture_size = 2
textures = np.ones((1, self.faces.shape[1], texture_size,
texture_size, texture_size, 3), 'float32')
self.textures = textures
# load reference image
if filename_ref is not None:
self.image_ref = (scipy.misc.imread(filename_ref).max(-1) !=
0).astype('float32')
else:
self.image_ref = None
# camera parameters
self.camera_position = chainer.Parameter(
np.array([6, 10, -14], 'float32'))
# setup renderer
renderer = neural_renderer.Renderer()
renderer.eye = self.camera_position
self.renderer = renderer
def __init__(self,
filename_obj,
dim_in=512,
centroid_scale=0.1,
bias_scale=1.0,
centroid_lr=0.1,
bias_lr=1.0):
super(Decoder, self).__init__()
# load .obj
vertices_base, faces = nr.load_obj(filename_obj)
# faces = faces[:, list(reversed(list(range(faces.shape[-1]))))]
self.register_buffer('vertices_base', vertices_base)
self.register_buffer('faces', faces)
self.laplacian_loss = LaplacianFaceLoss(vertices_base, faces)
self.nv = self.vertices_base.size(0)
self.nf = self.faces.size(0)
self.centroid_scale = centroid_scale
self.bias_scale = bias_scale
self.obj_scale = 0.5
dim = 1024
dim_hidden = [dim, dim * 2]
self.fc1 = nn.Linear(dim_in, dim_hidden[0])
self.fc2 = nn.Linear(dim_hidden[0], dim_hidden[1])
self.fc_centroid = nn.Linear(dim_hidden[1], 3)
self.fc_bias = nn.Linear(dim_hidden[1], self.nv * 3)
def __init__(self,
filename_obj,
dim_in=512,
centroid_scale=0.1,
bias_scale=1.0,
centroid_lr=0.1,
bias_lr=1.0):
super(Decoder, self).__init__()
self.vertices_base, self.faces = nr.load_obj(filename_obj)
self.vertices_base = self.vertices_base.to(device)
self.faces = self.faces.to(device)
self.num_vertices = self.vertices_base.shape[0]
self.num_faces = self.faces.shape[
0] # ToDO: add centroid_lr and bias_lr
self.centroid_scale = centroid_scale
self.bias_scale = bias_scale
self.obj_scale = 0.5
dim = 1024
dim_hidden = [dim, dim * 2]
self.linear1 = nn.Linear(dim_in, dim_hidden[0])
self.linear2 = nn.Linear(dim_hidden[0], dim_hidden[1])
self.linear_centroids = nn.Linear(dim_hidden[1], 3)
self.linear_bias = nn.Linear(dim_hidden[1], self.num_vertices * 3)
def run():
parser = argparse.ArgumentParser()
parser.add_argument('-i',
'--filename_input',
type=str,
default='./examples/data/teapot.obj')
parser.add_argument('-o',
'--filename_output',
type=str,
default='./examples/data/example1.gif')
parser.add_argument('-g', '--gpu', type=int, default=0)
args = parser.parse_args()
working_directory = os.path.dirname(args.filename_output)
# other settings
camera_distance = 2.732
elevation = 30
texture_size = 2
# load .obj
vertices, faces = neural_renderer.load_obj(args.filename_input)
vertices = vertices[
None, :, :] # [num_vertices, XYZ] -> [batch_size=1, num_vertices, XYZ]
faces = faces[None, :, :] # [num_faces, 3] -> [batch_size=1, num_faces, 3]
# create texture [batch_size=1, num_faces, texture_size, texture_size, texture_size, RGB]
textures = np.ones(
(1, faces.shape[1], texture_size, texture_size, texture_size, 3),
'float32')
# to gpu
chainer.cuda.get_device_from_id(args.gpu).use()
vertices = chainer.cuda.to_gpu(vertices)
faces = chainer.cuda.to_gpu(faces)
textures = chainer.cuda.to_gpu(textures)
# create renderer
renderer = neural_renderer.Renderer()
# draw object
for num, azimuth in enumerate(range(0, 360, 4)):
renderer.eye = neural_renderer.get_points_from_angles(
camera_distance, elevation, azimuth)
images = renderer.render(
vertices, faces,
textures) # [batch_size, RGB, image_size, image_size]
image = images.data.get()[0].transpose(
(1, 2, 0)) # [image_size, image_size, RGB]
scipy.misc.imsave('%s/_tmp_%04d.png' % (working_directory, num), image)
# generate gif (need ImageMagick)
options = '-delay 8 -loop 0 -layers optimize'
subprocess.call('convert %s %s/_tmp_*.png %s' %
(options, working_directory, args.filename_output),
shell=True)
# remove temporary files
for filename in glob.glob('%s/_tmp_*.png' % working_directory):
os.remove(filename)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-i',
'--filename_input',
type=str,
default=os.path.join(data_dir, 'teapot.obj'))
parser.add_argument('-o',
'--filename_output',
type=str,
default=os.path.join(data_dir, 'example1.gif'))
parser.add_argument('-g', '--gpu', type=int, default=0)
args = parser.parse_args()
# other settings
camera_distance = 2.732
elevation = 30
texture_size = 2
# load .obj
vertices, faces = nr.load_obj(args.filename_input)
vertices = torch.FloatTensor([[0, 0, 0], [0, 1.5, 0], [1, 0, 0]]).cuda()
faces = torch.IntTensor([[0, 1, 2]]).cuda()
# self.register_buffer('vertices', vertices[None, :, :])
# self.register_buffer('faces', faces[None, :, :])
vertices = vertices[
None, :, :] # [num_vertices, XYZ] -> [batch_size=1, num_vertices, XYZ]
faces = faces[None, :, :] # [num_faces, 3] -> [batch_size=1, num_faces, 3]
# create texture [batch_size=1, num_faces, texture_size, texture_size, texture_size, RGB]
textures = torch.ones(1,
faces.shape[1],
texture_size,
texture_size,
texture_size,
3,
dtype=torch.float32).cuda()
# to gpu
# create renderer
renderer = nr.Renderer(camera_mode='canonical')
# draw object
loop = tqdm.tqdm(range(0, 360, 4))
writer = imageio.get_writer(args.filename_output, mode='I')
for num, azimuth in enumerate(loop):
loop.set_description('Drawing')
renderer.eye = [0, 0, -5]
images, _, _ = renderer(
vertices, faces,
textures) # [batch_size, RGB, image_size, image_size]
image = images.detach().cpu().numpy()[0].transpose(
(1, 2, 0)) # [image_size, image_size, RGB]
imsave('./examples/tmp/_tmp_test.png', image)
# writer.append_data((255*image).astype(np.uint8))
writer.close()
def load_teapot_batch(batch_size=4, target_num=2):
vertices, faces = neural_renderer.load_obj('./tests/data/teapot.obj')
textures = np.ones((faces.shape[0], 4, 4, 4, 3), 'float32')
vertices, faces, textures = to_minibatch((vertices, faces, textures), batch_size, target_num)
vertices = chainer.cuda.to_gpu(vertices)
faces = chainer.cuda.to_gpu(faces)
textures = chainer.cuda.to_gpu(textures)
return vertices, faces, textures
def init_rasterizer(self, obj_path, global_RT):
self.cur_obj_path = obj_path
obj_data = {}
obj_data['v_attr'] , obj_data['f_attr'] = nr.load_obj(obj_path, normalization = False, use_cuda = False)
self.rasterizer = network.Rasterizer(self.cfg,
obj_data = obj_data,
# preset_uv_path = cfg.DATASET_FVV.UV_PATH,
global_RT = global_RT)
self.rasterizer.cuda()
def load_teapot_batch(batch_size=4, target_num=2):
vertices, faces = neural_renderer.load_obj('./tests/data/teapot.obj')
textures = np.ones((faces.shape[0], 4, 4, 4, 3), 'float32')
vertices, faces, textures = to_minibatch((vertices, faces, textures),
batch_size, target_num)
vertices = chainer.cuda.to_gpu(vertices)
faces = chainer.cuda.to_gpu(faces)
textures = chainer.cuda.to_gpu(textures)
return vertices, faces, textures
def __init__(self, filename_obj, batch_size=10, image_size=256):
super(VertexPredictor, self).__init__()
vertices, faces = nr.load_obj(filename_obj)
vertices[:,1] = - vertices[:,1]
vertices = vertices[None, :, :]
vertices = np.tile(vertices, (batch_size,1,1))
faces = faces[None, :, :]
faces = np.tile(faces, (batch_size,1,1))
self.vertices = nn.Parameter(torch.from_numpy(vertices))
self.register_buffer('faces', torch.from_numpy(faces))
def run():
parser = argparse.ArgumentParser()
parser.add_argument('-i',
'--filename_input',
type=str,
default='./examples/data/teapot.obj')
parser.add_argument('-o',
'--filename_output',
type=str,
default='./examples/data/example1.gif')
parser.add_argument('-g', '--gpu', type=int, default=0)
args = parser.parse_args()
working_directory = os.path.dirname(args.filename_output)
# other settings
camera_distance = 2.732
elevation = 30
# load .obj
# vertices: [num_vertices, XYZ]
# faces: # [num_faces, 3]
vertices, faces = neural_renderer.load_obj(args.filename_input)
vertices = vertices[None, :, :] # -> [batch_size=1, num_vertices, XYZ]
# to gpu
chainer.cuda.get_device_from_id(args.gpu).use()
vertices = chainer.cuda.to_gpu(vertices)
faces = chainer.cuda.to_gpu(faces)
# create renderer
renderer = neural_renderer.Renderer()
# draw object
loop = tqdm.tqdm(range(0, 360, 4))
for num, azimuth in enumerate(loop):
loop.set_description('Drawing')
renderer.viewpoints = neural_renderer.get_points_from_angles(
camera_distance, elevation, azimuth)
images = renderer.render_silhouettes(
vertices, faces) # [batch_size, RGB, image_size, image_size]
image = images.data.get()[0] # [image_size, image_size]
scipy.misc.toimage(image, cmin=0, cmax=1).save(
'%s/_tmp_%04d.png' % (working_directory, num))
# generate gif (need ImageMagick)
options = '-delay 8 -loop 0 -layers optimize'
subprocess.call('convert %s %s/_tmp_*.png %s' %
(options, working_directory, args.filename_output),
shell=True)
# remove temporary files
for filename in glob.glob('%s/_tmp_*.png' % working_directory):
os.remove(filename)
def test_texture(self):
renderer = neural_renderer.Renderer()
vertices, faces, textures = neural_renderer.load_obj(
'./tests/data/1cde62b063e14777c9152a706245d48/model.obj', load_texture=True)
vertices = chainer.cuda.to_gpu(vertices)
faces = chainer.cuda.to_gpu(faces)
textures = chainer.cuda.to_gpu(textures)
renderer.eye = neural_renderer.get_points_from_angles(2, 15, 30)
images = renderer.render(vertices[None, :, :], faces[None, :, :], textures[None, :, :, :, :, :]).data.get()
scipy.misc.imsave('./tests/data/car.png', scipy.misc.toimage(images[0]))
vertices, faces, textures = neural_renderer.load_obj(
'./tests/data/4e49873292196f02574b5684eaec43e9/model.obj', load_texture=True, texture_size=16)
vertices = chainer.cuda.to_gpu(vertices)
faces = chainer.cuda.to_gpu(faces)
textures = chainer.cuda.to_gpu(textures)
renderer.eye = neural_renderer.get_points_from_angles(2, 15, -90)
images = renderer.render(vertices[None, :, :], faces[None, :, :], textures[None, :, :, :, :, :]).data.get()
scipy.misc.imsave('./tests/data/display.png', scipy.misc.toimage(images[0]))
def test_tetrahedron(self):
vertices_ref = np.array(
[
[1., 0., 0.],
[0., 1., 0.],
[0., 0., 1.],
[0., 0., 0.]],
'float32')
faces_ref = np.array(
[
[1, 3, 2],
[3, 1, 0],
[2, 0, 1],
[0, 2, 3]],
'int32')
vertices, faces = neural_renderer.load_obj('./tests/data/tetrahedron.obj', False)
assert (np.allclose(vertices_ref, vertices))
assert (np.allclose(faces_ref, faces))
vertices, faces = neural_renderer.load_obj('./tests/data/tetrahedron.obj', True)
assert (np.allclose(vertices_ref * 2 - 1.0, vertices))
assert (np.allclose(faces_ref, faces))
def __init__(self, filename_obj, texture_size=4, normalization=True):
super(Mesh, self).__init__()
with self.init_scope():
# load .obj
vertices, faces = neural_renderer.load_obj(filename_obj, normalization)
self.vertices = chainer.Parameter(vertices)
self.faces = faces
self.num_vertices = self.vertices.shape[0]
self.num_faces = self.faces.shape[0]
# create textures
init = chainer.initializers.Normal()
shape = (self.num_faces, texture_size, texture_size, texture_size, 3)
self.textures = chainer.Parameter(init, shape)
self.texture_size = texture_size
def run():
parser = argparse.ArgumentParser()
parser.add_argument('-i', '--filename_input', type=str, default='./examples/data/teapot.obj')
parser.add_argument('-o', '--filename_output', type=str, default='./examples/data/example1.gif')
parser.add_argument('-g', '--gpu', type=int, default=0)
args = parser.parse_args()
working_directory = os.path.dirname(args.filename_output)
# other settings
camera_distance = 2.732
elevation = 30
texture_size = 2
# load .obj
vertices, faces = neural_renderer.load_obj(args.filename_input)
vertices = vertices[None, :, :] # [num_vertices, XYZ] -> [batch_size=1, num_vertices, XYZ]
faces = faces[None, :, :] # [num_faces, 3] -> [batch_size=1, num_faces, 3]
# create texture [batch_size=1, num_faces, texture_size, texture_size, texture_size, RGB]
textures = np.ones((1, faces.shape[1], texture_size, texture_size, texture_size, 3), 'float32')
# to gpu
chainer.cuda.get_device_from_id(args.gpu).use()
vertices = chainer.cuda.to_gpu(vertices)
faces = chainer.cuda.to_gpu(faces)
textures = chainer.cuda.to_gpu(textures)
# create renderer
renderer = neural_renderer.Renderer()
# draw object
loop = tqdm.tqdm(range(0, 360, 4))
for num, azimuth in enumerate(loop):
loop.set_description('Drawing')
renderer.eye = neural_renderer.get_points_from_angles(camera_distance, elevation, azimuth)
images = renderer.render(vertices, faces, textures) # [batch_size, RGB, image_size, image_size]
image = images.data.get()[0].transpose((1, 2, 0)) # [image_size, image_size, RGB]
scipy.misc.toimage(image, cmin=0, cmax=1).save('%s/_tmp_%04d.png' % (working_directory, num))
# generate gif (need ImageMagick)
options = '-delay 8 -loop 0 -layers optimize'
subprocess.call('convert %s %s/_tmp_*.png %s' % (options, working_directory, args.filename_output), shell=True)
# remove temporary files
for filename in glob.glob('%s/_tmp_*.png' % working_directory):
os.remove(filename)
def __init__(self, filename_obj, filename_ref):
super(Model, self).__init__()
with self.init_scope():
# load .obj
vertices, faces = neural_renderer.load_obj(filename_obj)
self.vertices = vertices[None, :, :]
self.faces = faces[None, :, :]
# create textures
texture_size = 4
textures = np.zeros((1, self.faces.shape[1], texture_size, texture_size, texture_size, 3), 'float32')
self.textures = chainer.Parameter(textures)
# load reference image
self.image_ref = scipy.misc.imread(filename_ref).astype('float32') / 255.
# setup renderer
renderer = neural_renderer.Renderer()
renderer.perspective = False
renderer.light_intensity_directional = 0.0
renderer.light_intensity_ambient = 1.0
self.renderer = renderer
def test_teapot(self):
vertices, faces = neural_renderer.load_obj('./tests/data/teapot.obj')
assert (faces.shape[0] == 2464)
assert (vertices.shape[0] == 1292)
def run():
parser = argparse.ArgumentParser()
parser.add_argument('-i', '--filename_input', type=str, default='./examples/data/teapot.obj')
parser.add_argument('-bs', '--batch_size', type=int, default=1)
parser.add_argument('-is', '--image_size', type=int, default=256)
parser.add_argument('-us', '--unsafe', type=int, default=0)
parser.add_argument('-g', '--gpu', type=int, default=0)
args = parser.parse_args()
# other settings
camera_distance = 2.732
elevation = 30
texture_size = 2
# load .obj
vertices, faces = neural_renderer.load_obj(args.filename_input)
vertices = vertices[None, :, :] # [num_vertices, XYZ] -> [batch_size=1, num_vertices, XYZ]
faces = faces[None, :, :] # [num_faces, 3] -> [batch_size=1, num_faces, 3]
# create texture [batch_size=1, num_faces, texture_size, texture_size, texture_size, RGB]
textures = np.ones((1, faces.shape[1], texture_size, texture_size, texture_size, 3), 'float32')
# tile to minibatch
vertices = np.tile(vertices, (args.batch_size, 1, 1))
faces = np.tile(faces, (args.batch_size, 1, 1))
textures = np.tile(textures, (args.batch_size, 1, 1, 1, 1, 1))
# to gpu
chainer.cuda.get_device_from_id(args.gpu).use()
vertices = chainer.Variable(chainer.cuda.to_gpu(vertices))
faces = chainer.cuda.to_gpu(faces)
textures = chainer.Variable(chainer.cuda.to_gpu(textures))
# create renderer
renderer = neural_renderer.Renderer()
renderer.image_size = args.image_size
# draw object
times_forward = []
times_backward = []
loop = tqdm.tqdm(range(0, 360, 15))
for num, azimuth in enumerate(loop):
loop.set_description('Drawing')
renderer.eye = neural_renderer.get_points_from_angles(camera_distance, elevation, azimuth)
time_start = time.time()
images = renderer.render_silhouettes(vertices, faces) # [batch_size, image_size, image_size]
_ = images.data[0, 0, 0].get()
time_end = time.time()
times_forward.append(time_end - time_start)
loss = chainer.functions.sum(images)
_ = loss.data.get()
time_start = time.time()
loss.backward()
time_end = time.time()
times_backward.append(time_end - time_start)
print 'silhouette forward time: %.3f ms' % (np.sum(times_forward[1:]) / len(times_forward[1:]))
print 'silhouette backward time: %.3f ms' % (np.sum(times_backward[1:]) / len(times_backward[1:]))
# draw object
times_forward = []
times_backward = []
loop = tqdm.tqdm(range(0, 360, 15))
for num, azimuth in enumerate(loop):
loop.set_description('Drawing')
renderer.eye = neural_renderer.get_points_from_angles(camera_distance, elevation, azimuth)
time_start = time.time()
images = renderer.render(vertices, faces, textures) # [batch_size, RGB, image_size, image_size]
_ = images.data[0, 0, 0, 0].get()
time_end = time.time()
times_forward.append(time_end - time_start)
loss = chainer.functions.sum(images)
_ = loss.data.get()
time_start = time.time()
loss.backward()
time_end = time.time()
times_backward.append(time_end - time_start)
print 'texture forward time: %.3f ms' % (np.sum(times_forward[1:]) / len(times_forward[1:]))
print 'texture backward time: %.3f ms' % (np.sum(times_backward[1:]) / len(times_backward[1:]))