kwea123/nerf_pl

Health v2 · maintenance only

Adoption not part of the score

2805 stars · 458 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

An unofficial PyTorch implementation of NeRF (Neural Radiance Fields) and NeRF in the Wild built on pytorch-lightning, supporting multi-GPU training, colored mesh reconstruction, and real-time volume rendering in Unity. It prioritizes simpler, faster training and readable code over strict paper reproducibility.

Use cases

• train a nerf model from photos
• reconstruct 3d mesh from images
• novel view synthesis of a scene
• render nerf scenes in unity
• run nerf training on colab
• understand how nerf works from code
• create mixed reality scenes from radiance fields

When to choose

• you want a readable, well-commented NeRF implementation for learning
• you need multi-GPU training or Colab notebooks for easy experimentation
• you want to export meshes or render scenes in Unity

When to avoid

• you need fast, high-quality NeRF training - use instant-ngp or ngp_pl instead
• you need strict paper reproducibility of the official NeRF results
• you need active support for dynamic scenes - see nsff_pl

Facets

library · maturity maintenance

machine-learning deep-learning graphics simulation computer-vision graphics deep-learning machine-learning python cross-platform nerf neural-radiance-fields view-synthesis volume-rendering pytorch-lightning 3d-reconstruction mesh-reconstruction unity-integration colab-notebooks nerf-in-the-wild gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="kwea123/nerf_pl")