Victor Czech

If your evaluation data differs from the training data (like big differences in the number of points or label distributions), this could cause problems with the running statistics of batch...

There are two things you could try: 1. Train on a dataset specific for bike models. ShapeNet contains significanty more plane models (4045) than bike models (59): https://shapenet.org/taxonomy-viewer 2. Crop...

Hello, I have the same problem, as shown in the error message the code uses both tab characters and softtabs (4 tabs in a row) for indentation in the same...

@zParquet I am wondering the same and searching for quite a while now, because the gap is quite large. Two differences I found so far are: 1) Here, small eps...

After reading the appendix E.3, it seems a huge benefit comes from a (very) large number of rays in each batch, at the cost of fewer samples. However these fewer...

Unfortunately no, but as far as I remember it was basically the code from the repo linked above. Note the 20x speedup refers to the sampling method only and not...

Hello, the correct formula given in the zip NeRF paper is  It originates from the original mip NeRF paper, where they defined the cone radius of a pixel at...