apple/ml-neuman

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1285 stars · 147 forks observed · 2026-10-07

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

Official reference implementation of NeuMan (ECCV 2022), which reconstructs an animatable human and the background scene from a single video using neural radiance fields. It supports novel view synthesis, novel pose synthesis, and compositional rendering of humans into new scenes.

Use cases

• reconstruct a 3D animatable human from a single video
• novel view synthesis of a scene with a person
• render a person in new poses from monocular video
• composite a reconstructed human into a new background scene
• research baseline for human NeRF methods

When to choose

• you need a research-grade implementation of human radiance fields from monocular video
• you want to reproduce or extend the NeuMan paper
• you have SMPL model access and a CUDA GPU for training/inference

When to avoid

• you need a production-ready or user-friendly 3D scanning tool
• you cannot obtain SMPL body model weights due to registration requirements
• you need real-time performance or non-PyTorch environments

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing graphics simulation computer-vision machine-learning graphics deep-learning python neural-radiance-fields nerf human-reconstruction novel-view-synthesis smpl 3d-reconstruction research-code eccv-2022 linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="apple-aiml-research/ml-neuman")