zju3dv/UniVerse
[ICCV 2025] UniVerse: Unleashing the Scene Prior of Video Diffusion Models for Robust Radiance Field Reconstruction
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.
Stars
27
Forks
—
Language
—
License
—
Category
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.
Higher-rated alternatives
jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...