# apple/ml-neuman

Official repository of NeuMan: Neural Human Radiance Field from a Single Video (ECCV 2022)

Repository: https://github.com/apple/ml-neuman
Canonical: https://ross.abutalabs.com/products/ml-neuman
Language: Python
License: NOASSERTION
License Family: other
Last push: 2023-05-23T14:27:10+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1505, "days_push": 1198, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1286, forks 149 (observed 2026-08-28T04:04:14.924222+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing, graphics, simulation
- domain: computer-vision, machine-learning, graphics, deep-learning
- platform: python
- tags: neural-radiance-fields, nerf, human-reconstruction, novel-view-synthesis, smpl, 3d-reconstruction, research-code, eccv-2022, linux, gpu

## Member repositories
- apple/ml-neuman (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:14.924222+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:56:08.256630+00:00, confidence not recorded.
  - readme: https://github.com/apple/ml-neuman (fetched 2026-08-28T04:04:14.924222+00:00, sha eb7d192d6bb6)
- Data as of 2026-08-30T08:39:29.467469+00:00.