def test_orthographic(self):
far = 10.0
near = 1.0
cameras = OpenGLOrthographicCameras(znear=near, zfar=far)
P = cameras.get_projection_transform()
vertices = torch.tensor([1, 2, far], dtype=torch.float32)
projected_verts = torch.tensor([1, 2, 1], dtype=torch.float32)
vertices = vertices[None, None, :]
v1 = P.transform_points(vertices)
v2 = orthographic_project_naive(vertices)
self.assertTrue(torch.allclose(v1[..., :2], v2[..., :2]))
self.assertTrue(torch.allclose(v1.squeeze(), projected_verts))
vertices[..., 2] = near
projected_verts[2] = 0.0
v1 = P.transform_points(vertices)
v2 = orthographic_project_naive(vertices)
self.assertTrue(torch.allclose(v1[..., :2], v2[..., :2]))
self.assertTrue(torch.allclose(v1.squeeze(), projected_verts))
def test_orthographic_mixed_inputs_grad(self):
far = torch.tensor([10.0])
near = 1.0
scale = torch.tensor([[1.0, 1.0, 1.0]], requires_grad=True)
cameras = OpenGLOrthographicCameras(znear=near,
zfar=far,
scale_xyz=scale)
P = cameras.get_projection_transform()
vertices = torch.tensor([1.0, 2.0, 10.0], dtype=torch.float32)
vertices_batch = vertices[None, None, :]
v1 = P.transform_points(vertices_batch)
v1.sum().backward()
self.assertTrue(hasattr(scale, "grad"))
scale_grad = scale.grad.clone()
grad_scale = torch.tensor([[
vertices[0] * P._matrix[:, 0, 0],
vertices[1] * P._matrix[:, 1, 1],
vertices[2] * P._matrix[:, 2, 2],
]])
self.assertTrue(torch.allclose(scale_grad, grad_scale))
def __init__(self, meshes, image_size=256, device='cuda'):
super(ColorRenderer, self).__init__()
self.meshes = meshes
cameras = OpenGLOrthographicCameras(device=device)
raster_settings = RasterizationSettings(image_size=image_size,
blur_radius=0.0,
faces_per_pixel=1,
bin_size=0)
lights = PointLights(device=device, location=((2.0, 2.0, -2.0), ))
self.renderer = MeshRenderer(
rasterizer=MeshRasterizer(cameras=cameras,
raster_settings=raster_settings),
shader=TexturedSoftPhongShader(device=device, lights=lights))
def __init__(self, meshes: Meshes, image_size=256):
"""
Initialization of the Renderer Class. Instances of the mask and depth renderer are create on corresponding
device.
:param device: The device, on which the computation is done.
:param image_size: Image size for the rasterization. Default is 256.
"""
super().__init__()
self.meshes = meshes
device = meshes.device
# TODO: check how to implement weak perspective (scaled orthographic).
cameras = OpenGLOrthographicCameras(device=device)
self._rasterizer = MeshRasterizer(
cameras=cameras,
raster_settings=RasterizationSettings(image_size=image_size,
faces_per_pixel=100))
self._shader = SoftSilhouetteShader(
blend_params=(BlendParams(sigma=1e-4, gamma=1e-4)))
def __init__(self, meshes: Meshes, device: str, image_size: int = 256):
"""
Initialization of DepthRenderer. Initialization of the default mesh rasterizer and silhouette shader which is
used because of simplicity.
:param device: The device, on which the computation is done, e.g. cpu or cuda.
:param image_size: Image size for the rasterization. Default is 256.
:param meshes: A batch of meshes. pytorch3d.structures.Meshes. Dimension meshes in R^N.
View https://github.com/facebookresearch/pytorch3d/blob/master/pytorch3d/structures/meshes.py
for additional information.
"""
super(DepthRenderer, self).__init__()
self._meshes = meshes
# TODO: check how to implement weak perspective (scaled orthographic).
cameras = OpenGLOrthographicCameras(device=device)
raster_settings = RasterizationSettings(image_size=image_size)
self._rasterizer = MeshRasterizer(cameras=cameras,
raster_settings=raster_settings)
self._shader = SoftSilhouetteShader(
blend_params=(BlendParams(sigma=1e-4, gamma=1e-4)))
def test_pointcloud_with_features(self):
device = torch.device("cuda:0")
file_dir = Path(__file__).resolve().parent.parent / "docs/tutorials/data"
pointcloud_filename = file_dir / "PittsburghBridge/pointcloud.npz"
# Note, this file is too large to check in to the repo.
# Download the file to run the test locally.
if not path.exists(pointcloud_filename):
url = "https://dl.fbaipublicfiles.com/pytorch3d/data/PittsburghBridge/pointcloud.npz"
msg = (
"pointcloud.npz not found, download from %s, save it at the path %s, and rerun"
% (url, pointcloud_filename)
)
warnings.warn(msg)
return True
# Load point cloud
pointcloud = np.load(pointcloud_filename)
verts = torch.Tensor(pointcloud["verts"]).to(device)
rgb_feats = torch.Tensor(pointcloud["rgb"]).to(device)
verts.requires_grad = True
rgb_feats.requires_grad = True
point_cloud = Pointclouds(points=[verts], features=[rgb_feats])
R, T = look_at_view_transform(20, 10, 0)
cameras = OpenGLOrthographicCameras(device=device, R=R, T=T, znear=0.01)
raster_settings = PointsRasterizationSettings(
# Set image_size so it is not a multiple of 16 (min bin_size)
# in order to confirm that there are no errors in coarse rasterization.
image_size=500,
radius=0.003,
points_per_pixel=10,
)
renderer = PointsRenderer(
rasterizer=PointsRasterizer(
cameras=cameras, raster_settings=raster_settings
),
compositor=AlphaCompositor(),
)
images = renderer(point_cloud)
# Load reference image
filename = "bridge_pointcloud.png"
image_ref = load_rgb_image("test_%s" % filename, DATA_DIR)
for bin_size in [0, None]:
# Check both naive and coarse to fine produce the same output.
renderer.rasterizer.raster_settings.bin_size = bin_size
images = renderer(point_cloud)
rgb = images[0, ..., :3].squeeze().cpu()
if DEBUG:
filename = "DEBUG_%s" % filename
Image.fromarray((rgb.detach().numpy() * 255).astype(np.uint8)).save(
DATA_DIR / filename
)
self.assertClose(rgb, image_ref, atol=0.015)
# Check grad exists.
grad_images = torch.randn_like(images)
images.backward(grad_images)
self.assertIsNotNone(verts.grad)
self.assertIsNotNone(rgb_feats.grad)