Richard Shaw

Results 17 comments of Richard Shaw

Hey thanks for the reply. I have now implemented the LLFF dataloader with examples/train_mlp_nerf.py, but unfortunately I am getting slightly worse results than vanilla nerf or TensoRF. On the fern...

Great thank you!

Here's some code that runs out of memory for me: ``` device = "cuda" if torch.cuda.is_available() else "cpu" dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] >= 8 else torch.float16 images = torch.rand(([60,...

You mean you don’t apply any bilateral filter at test time?

Thanks for your response! Using your timing script with the same example images I get: images [20, 3, 350, 518] = 1.9080 s images [60, 3, 350, 518] = 11.7003...

Do we need to compute point tracks to do BA? We need 2D-3D correspondences right? For Table 1 in your paper, is it just one global BA optimization for all...