def __getitem__(self, idx):
intrinsics, _, _, _ = util.parse_intrinsics(os.path.join(self.instance_dir, "intrinsics.txt"),
trgt_sidelength=self.img_sidelength)
intrinsics = torch.Tensor(intrinsics).float()
rgb = data_util.load_rgb(self.color_paths[idx], sidelength=self.img_sidelength)
rgb = rgb.reshape(3, -1).transpose(1, 0)
pose = data_util.load_pose(self.pose_paths[idx])
if self.has_params:
params = data_util.load_params(self.param_paths[idx])
else:
params = np.array([0])
uv = np.mgrid[0:self.img_sidelength, 0:self.img_sidelength].astype(np.int32)
uv = torch.from_numpy(np.flip(uv, axis=0).copy()).long()
uv = uv.reshape(2, -1).transpose(1, 0)
sample = {
"instance_idx": torch.Tensor([self.instance_idx]).squeeze(),
"rgb": torch.from_numpy(rgb).float(),
"pose": torch.from_numpy(pose).float(),
"uv": uv,
"param": torch.from_numpy(params).float(),
"intrinsics": intrinsics
}
return sample
default=np.sqrt(3) / 2,
help='Position of the near plane.')
opt = parser.parse_args()
print('\n'.join(["%s: %s" % (key, value) for key, value in vars(opt).items()]))
device = torch.device('cuda')
input_image_dims = [opt.img_sidelength, opt.img_sidelength]
proj_image_dims = [
64, 64
] # Height, width of 2d feature map used for lifting and rendering.
# Read origin of grid, scale of each voxel, and near plane
_, grid_barycenter, scale, near_plane, _ = \
util.parse_intrinsics(os.path.join(opt.data_root, 'intrinsics.txt'), trgt_sidelength=input_image_dims[0])
if near_plane == 0.0:
near_plane = opt.near_plane
# Read intrinsic matrix for lifting and projection
lift_intrinsic = util.parse_intrinsics(os.path.join(opt.data_root,
'intrinsics.txt'),
trgt_sidelength=proj_image_dims[0])[0]
proj_intrinsic = lift_intrinsic
# Set up scale and world coordinates of voxel grid
voxel_size = (1. / opt.grid_dim) * 1.1 * scale
grid_origin = torch.tensor(np.eye(4)).float().to(device).squeeze()
grid_origin[:3, 3] = grid_barycenter