yenchenlin/nerf-pytorch

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

6044 stars · 1122 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the original paper's results for synthesizing novel views of complex scenes, running 1.3x faster than the authors' TensorFlow code. It includes example datasets, pre-trained models, and config-driven training scripts.

Use cases

• train a NeRF model on synthetic or real image data
• generate novel views of a 3D scene from posed photographs
• reproduce NeRF paper results in PyTorch
• render spiral videos and depth maps of a scene
• learn how NeRF is implemented
• run NeRF on custom real-world captures with COLMAP poses

When to choose

• you want a faithful, numerically verified PyTorch port of the original NeRF
• you need a simple, well-known reference implementation for research or education
• you have a CUDA GPU and want faster training than the original TensorFlow code

When to avoid

• you need newer, faster NeRF variants like Instant-NGP or Mip-NeRF
• you need production-ready 3D reconstruction pipelines
• you have no GPU, since training takes hours even on a 2080 Ti

Facets

library · maturity maintenance

machine-learning deep-learning image-processing graphics computer-vision deep-learning graphics machine-learning python windows nerf neural-radiance-fields novel-view-synthesis pytorch 3d-reconstruction research-code gpu linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="yenchenlin/nerf-pytorch")