Discussion on Visual feature aggregation

Thanks again for releasing the code. I was going through extract_features.py and found that to calculate the feature for a voxel, visibility of the voxel is not considered from a given camera.

Intuitively, I thought that features would be averaged only from rendered views from which a particular voxel is available. Do have any explanation why does visibility does not matter? Did you guys tried something like this before finalizing the current method?