zju3dv/UniVerse

[ICCV 2025] UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction

16
/ 100
Experimental

This project helps 3D artists, game developers, and virtual reality creators build realistic 3D scenes from videos, even if the video quality is imperfect. It takes standard video footage as input and outputs a high-quality 3D representation of the scene, ready for use in various applications. This is for professionals who need to reconstruct complex real-world environments digitally.

No commits in the last 6 months.

Use this if you need to create detailed 3D models of real-world environments and objects directly from video recordings, especially when dealing with less-than-perfect source footage.

Not ideal if you're looking for a tool to generate abstract 3D art or models that don't need to accurately reflect a real-world scene captured by video.

3D-reconstruction virtual-reality-development game-asset-creation visual-effects digital-twin-creation
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 7 / 25
Community 0 / 25

How are scores calculated?

Stars

27

Forks

Language

License

Last pushed

Oct 03, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/zju3dv/UniVerse"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.