Open Zhiyuan-R opened 1 year ago
It may miss relu layer to the output of the alpha. In current implementation, the alpha can be negative!
Actually, the output of NeRF raw is applied ReLU in this line: https://github.com/yenchenlin/nerf-pytorch/blob/223fe62d87d641e2bb0fb5bdbbcb6dad5efb2af3/run_nerf.py#L275
raw
It may miss relu layer to the output of the alpha. In current implementation, the alpha can be negative!