yashbhalgat/HashNeRF-pytorch
A pure PyTorch implementation of NVIDIA's Instant-NGP paper for fast Neural Radiance Field training using multi-resolution hash encoding.
Not currently ranked — collecting fresh signals.
star history
This project reimplemented NVIDIA’s Instant-NGP method for training NeRFs in pure PyTorch, replacing the original C++/CUDA implementation. It achieves significantly faster convergence by using multi-resolution hash encoding to represent neural graphics primitives, enabling training of neural radiance fields up to 100x faster than vanilla NeRF on a single GPU. The implementation builds on the NeRF-pytorch codebase and provides additional loss options including total variation loss and sparsity-inducing loss.
Frequently asked
- What is yashbhalgat/HashNeRF-pytorch?
- A pure PyTorch implementation of NVIDIA's Instant-NGP paper for fast Neural Radiance Field training using multi-resolution hash encoding.
- Is HashNeRF-pytorch open source?
- Yes — yashbhalgat/HashNeRF-pytorch is open source, released under the MIT license.
- What language is HashNeRF-pytorch written in?
- yashbhalgat/HashNeRF-pytorch is primarily written in Python.
- How popular is HashNeRF-pytorch?
- yashbhalgat/HashNeRF-pytorch has 1k stars on GitHub.
- Where can I find HashNeRF-pytorch?
- yashbhalgat/HashNeRF-pytorch is on GitHub at https://github.com/yashbhalgat/HashNeRF-pytorch.