Open tangtaogo opened 1 year ago
Hi, thanks for your great work! In the code and tutorial, the depth supervision is conducted on the rendered_depth. But in paper the depth supervision is on ray termination, i.e., h(t).
Both of them are different ways of depth supervision. We provide both losses in the code.
Are they depth_loss and sigma_loss in the code, i.e., DS-NeRF&MSE and DS-NeRF&KL divergence in the paper respectively?
Hi, thanks for your great work! In the code and tutorial, the depth supervision is conducted on the rendered_depth. But in paper the depth supervision is on ray termination, i.e., h(t).