# DeepMotionEditing/deep-motion-editing

An end-to-end library for editing and rendering motion of 3D characters with deep learning [SIGGRAPH 2020]

Repository: https://github.com/DeepMotionEditing/deep-motion-editing
Canonical: https://ross.abutalabs.com/products/deep-motion-editing
Language: Python
License: BSD-2-Clause
License Family: permissive
Topics: character-animation, computer-graphics, deep-learning, motion-retargeting, style-transfer, computer-animation
Last push: 2024-07-12T15:05:13+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": 2326, "days_push": 782, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1722, forks 261 (observed 2026-08-28T04:05:27.851116+00:00)

## What it is
A PyTorch-based end-to-end library for editing and rendering 3D character motion, built on SIGGRAPH 2020 research. It provides deep learning modules for motion retargeting and motion style transfer, with visualization and rendering via Blender.

## Use cases
- retarget motion from one 3D character skeleton to another
- transfer motion style from video to animation
- edit bvh animation files with deep learning
- render 3D character animations in Blender
- reproduce SIGGRAPH 2020 motion retargeting results
- run cross-structural character animation retargeting

## When to choose
- you need deep-learning-based motion retargeting between character skeletons
- you want to apply motion styles from video to 3D animations
- you work with bvh animation files and PyTorch
- you need a research-grade reference implementation of skeleton-aware networks

## When to avoid
- you need a production animation tool with a polished GUI
- you work with formats other than bvh without conversion
- you need real-time animation editing on CPU only
- you want actively developed features - the library is largely research code

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, animation, graphics, image-processing
- domain: deep-learning, machine-learning, simulation
- platform: python
- tags: character-animation, motion-retargeting, motion-style-transfer, bvh, blender, pytorch, siggraph, computer-graphics, linux, macos, gpu

## Member repositories
- DeepMotionEditing/deep-motion-editing (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:27.851116+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 2026-08-30T03:33:58.474819+00:00, confidence not recorded.
  - readme: https://github.com/DeepMotionEditing/deep-motion-editing (fetched 2026-08-28T04:05:27.851116+00:00, sha c09af1fea2a6)
- Data as of 2026-08-30T08:39:29.467469+00:00.