zju3dv/GVHMR

Some data may be outdated — see provenance labels.

Code for "GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates", Siggraph Asia 2024, TPAMI 2026 observed · 2026-10-05

github.com/zju3dv/GVHMR · homepage · Jupyter Notebook · NOASSERTION (other) observed · 2026-10-05

Health v2 · maintenance only

66/100

Activity 95
Release rhythm 35
Longevity 55

Flags: no_releases no_license

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.

gap_med: n/a
age_days: 776
days_rel: n/a
days_push: 35
n_releases_24m: 0

Full methodology

Adoption not part of the score

2059 stars · 252 forks observed · 2026-10-05

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

GVHMR is a research codebase implementing the SIGGRAPH Asia 2024 paper 'World-Grounded Human Motion Recovery via Gravity-View Coordinates'. It recovers world-grounded global 3D human motion (SMPL poses) from monocular video using a gravity-view coordinate representation, with training and inference pipelines.

Use cases

recover 3d human motion from monocular video
estimate world-grounded smpl poses from video
run human pose estimation on a video with a static or moving camera
reproduce 3dpw rich and emdb benchmark results
train a human motion recovery model on amass bedlam datasets
demo human motion capture from a single video

When to choose

you need global (world-grounded) human motion rather than per-frame camera-relative pose
you want to reproduce or build on a published state-of-the-art motion recovery method
you have a GPU and want research-grade training and inference code

When to avoid

you need a production-ready commercial product (license is non-commercial)
you need real-time motion capture on CPU-only hardware
you only need simple 2D pose estimation

Facets

library · maturity active

machine-learning computer-vision deep-learning simulation computer-vision machine-learning artificial-intelligence python human-motion-recovery pose-estimation smpl monocular-video pytorch 3d-human-pose world-grounded-motion research-code gpu linux

3 sources

readme: https://github.com/zju3dv/GVHMR · fetched 2026-10-05 · 0c4b6b619bcf
homepage: https://zju3dv.github.io/gvhmr · fetched 2026-08-29 · 763e52f4169b
registry_pypi: https://pypi.org/pypi/gvhmr/json · fetched 2026-08-29 · 2b58302d01f0

Member repositories

Repository	Role	Health v2
zju3dv/GVHMR	main	66

For agents

markdown · JSON · MCP: product_card(name="zju3dv/GVHMR")

Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem