Closed CSU-NXY closed 1 year ago
Sorry I misunderstood. The loss is computed with minimum instead of maximum, so the implementation is correct. https://github.com/google-research/multinerf/blob/b02228160d3179300c7d499dca28cb9ca3677f32/internal/train_utils.py#L167
Hi, I noticed that in
orientation_loss
, the viewdirs are multiplied with -1. The comment says this is to represent normalized vectors from point to camera.This seems to be different with equation 11 in ref-nerf paper. Could you please give me some hints about it?