Davidyao99/uni4d
[CVPR 2025] Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video
This project helps visual effects artists, game developers, or researchers generate detailed 3D models with movement information from a standard video. You provide a single video of a moving object or scene, and it produces a '4D' representation, which is a 3D model that also captures how objects in the video move over time. This is useful for creating digital assets or analyzing motion.
222 stars. No commits in the last 6 months.
Use this if you need to create a dynamic 3D model of an object or scene from a single video, without needing specialized equipment or multiple camera angles.
Not ideal if you require real-time processing or very minimal computational resources, as it involves several complex vision models.
Stars
222
Forks
13
Language
Python
License
MIT
Category
Last pushed
May 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Davidyao99/uni4d"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
col14m/cadrille
[ICLR2026] cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning
filaPro/cad-recode
[ICCV2025] CAD-Recode: Reverse Engineering CAD Code from Point Clouds
pengsongyou/openscene
[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies
worldbench/3EED
[NeurIPS 2025 DB Track] 3EED: Ground Everything Everywhere in 3D
cambrian-mllm/cambrian-s
Cambrian-S: Towards Spatial Supersensing in Video