vid2player3dnv-tlabs/vid2player3d
Reconstructs physically simulatable 3D characters from monocular video, solving the problem that video motions are hard …
No ratings yet
Rate this skill
Stars344
Forks33
Watchers344
Open Issues5
InstallOne-line install
UnconfirmedWhether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:
git clone https://github.com/nv-tlabs/vid2player3d.git
OverviewOverview
Key Features
Reconstructs physically simulatable 3D characters from monocular video, solving the problem that video motions are hard to use directly in physics simulation. Key capabilities include: 1. Video-to-3D character reconstruction: extracts human motion from monocular video and reconstructs a 3D character with physical properties, so motions from video can be used directly in a simulator; 2. Motion imitation policy training: trains reinforcement learning motion imitation policies based on the reconstructed character and reference motion, enabling the simulated character to reproduce motions from the video; 3. Physics simulation interaction: drives the reconstructed character in a physics simulation environment and supports physically plausible interaction with scene objects.
Use Cases
Generating physically simulatable 3D characters from video footage, training character motion imitation policies, building reinforcement learning character control environments, generating interactive 3D character animations.
Target Roles
AI / Algorithm Engineer, Film/TV Director / Audio-Video Producer, Full-Stack / Indie Developer.
TopicsTopics
RatingUser ratings
Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.
RepositoryRepository
| Skill ID | 2196 |
|---|---|
| Data source | GitHub |
| Repository | nv-tlabs/vid2player3d |
| Category | AI & Machine Learning / Character Animation & Physics Simulation |
| Primary language | Python |
| License | Other |
| Default branch | main |
| GitHub repository ID | 712121619 |
| Node ID | R_kgDOKnIdEw |
| Rank | #1699 (position within the source ranking) |
| Site-wide popularity rank | #1915 (computed live from Stars, across all 5833 entries) |
GrowthStar / Fork growth
Still collecting
First record taken on 2026-09-22. Two days of data are needed before a trend line can be drawn.
TimelineTimeline
Repository created2023-10-30 20:43:432023-10-30
Data last updated2026-10-26 12:21:1121 days ago
Last commit2025-12-05 19:59:4111 months ago
CommitLatest commit
Committed by Haotianz94. Update Category: Documentation Updates. Commit details: Update README.md. This update refines the documentation for easier onboarding.