Open M11pha opened 3 weeks ago
Hello, on the line 155 of gaussian_model.py, should features[:, 3:, 1:] = 0.0 be features[:, :3, 1:] = 0.0 instead?
gaussian_model.py
features[:, 3:, 1:] = 0.0
features[:, :3, 1:] = 0.0
def create_from_pcd(self, pcd : BasicPointCloud, cam_infos : int, spatial_lr_scale : float): self.spatial_lr_scale = spatial_lr_scale fused_point_cloud = torch.tensor(np.asarray(pcd.points)).float().cuda() fused_color = RGB2SH(torch.tensor(np.asarray(pcd.colors)).float().cuda()) features = torch.zeros((fused_color.shape[0], 3, (self.max_sh_degree + 1) ** 2)).float().cuda() features[:, :3, 0 ] = fused_color features[:, 3:, 1:] = 0.0
The line is even redundant.
Yes, I think it was originally written this way to deliberately emphasize the point.
Hello, on the line 155 of
gaussian_model.py
, shouldfeatures[:, 3:, 1:] = 0.0
befeatures[:, :3, 1:] = 0.0
instead?