nerfacc
nerfacc copied to clipboard
nerfstudio-project
A General NeRF Acceleration Toolbox in PyTorch.
Hi, I tested on my datasets. Then I found the network can learn better when early_stop_eps=1 than early_stop_eps=1e-3 in ray_marching function, which makes no sense to me. It seems like...
hello , I want to visualize the predicted image when training to show the efficiency of ngp. Is there any relevant settings in the code ?
While running the examples, I got this error after running the train file for 20,000 steps. Sure my GPU architecture is 61, and does not support FullyFusedMLP, but it should...
Hi, Is there any way to extract actual visibility values from the rendering process? Currently the visibility test returns a mask of visible / invisible samples, but what I want...
This repo contains submodule so one needs either `git clone --recursive` or `git submodule update --recursive --init` after cloning the repo. It is worth nothing in the readme.
Thanks for sharing this great tool. Very exciting stuff. This is more of a question out of curiosity than an issue so please feel free to let me know if...
In my case, the nerf network may contains B different scenes. Can nerfacc support ray_marching with rays_o, rays_d (shape: B, N, 3) and sigma_fn (B, N, 3 -> B, N,...
When I try running the trainval.py script, I run into the following error after training is completed (during eval). I tried reducing the test_chunk_size as well as the target_sample_batch_size to...
Currently, nerfacc crashes on Win because long resolves to int32_t there rather than int64_t like on Linux.
Hello, It may be a easy problem to solve but I have not be able to do it. When running `python examples/train_ngp_nerf_occ.py --scene lego --data_root path` I get the following...
Metadata
Owner
Metadata
A General NeRF Acceleration Toolbox in PyTorch.