Train with multi-objects for 2D image regression

[jingma-git]

This is a very excellent work. I've tested it. It performs very well for image regression and novel-view thesis on 'single-object'. But when I try to train it with multiple objects from same category, the proposed methods seems not work very well. I am trying to figure out a solution to this problem: given images of multi-objects from same category, predict image under certain view for a specific object. This is my code for multi-objects training https://github.com/jingma-git/NeRF_Pytorch. Any insights to solve this problem? Here is some useful links: https://github.com/thunguyenphuoc/HoloGAN

[phongnhhn92]

I think you are misunderstanding the problem that NERF is trying to solve. NERF is solving the problem of view synthesis on a specific scene. NERF can not generalize to a set of objects that you are showing in your implementation. In fact, HoloGAN is trying to solve another problem which is synthesizing images from the same category. Therefore, you should not compare NERF and HoloGAN directly.