some questions about depth_loss

[LiXinghui-666]

Thank you for your excellent work. I would like to know why is this operation performed on depth_gt when depth loss is calculated：(depth_gt * 50 + 0.5). Corresponding to this line of code:

def get_depth_loss(self, depth_pred, depth_gt, mask):
        # TODO remove hard-coded scaling for depth
        return self.depth_loss(depth_pred.reshape(1, 32, 32), (depth_gt * 50 + 0.5).reshape(1, 32, 32), mask.reshape(1, 32, 32))

[niujinshuchong]

Hi, the monocular depth output is small and it's in the range of 0.01 to 0.04, and the loss will be very small so we simply scale them to some large value.

[LiXinghui-666]

Thank you for your reply!

[LiXinghui-666]

culart

Hi, the monocular depth output is small and it's in the range of 0.01 to 0.04, and the loss will be very small so we simply scale them to some large value.

There's the same question about scale scaling. Since a scale and shift are calculated in advance when the depth loss is calculated, what is the function of the following line in the code?

# we should use unnormalized ray direction for depth
ray_dirs_tmp, _ = rend_util.get_camera_params(uv, torch.eye(4).to(pose.device)[None], intrinsics)
depth_scale = ray_dirs_tmp[0, :, 2:]
depth_values = depth_scale * depth_values