Y-Research-SBU/Ouroboros
Official Repository for Ouroboros - ICCV 2025
This tool helps 3D artists, game developers, and architectural visualizers efficiently break down or build up realistic images. It takes a regular image or video and extracts its core material properties like color, surface texture, and lighting, or it can take these properties and reconstruct a new, consistent image. This enables faster creative iteration and ensures visual elements remain consistent across different rendering tasks.
Use this if you need to quickly decompose images into their underlying material properties or synthesize new, realistic images and videos from specified material properties with strong visual consistency.
Not ideal if you require highly specialized, manually-tuned rendering control or are not working with photorealistic 3D assets and environments.
Stars
20
Forks
—
Language
Python
License
MIT
Category
Last pushed
Nov 12, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/Y-Research-SBU/Ouroboros"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
soran-ghaderi/torchebm
🍓 Build and train energy-based and diffusion models in PyTorch ⚡.
spqb/adabmDCApy
Pytorch implementation of adabmDCA
opendilab/GenerativeRL
Python library for solving reinforcement learning (RL) problems using generative models (e.g....
AstraZeneca/DiffAbXL
The official implementation of DiffAbXL benchmarked in the paper "Exploring Log-Likelihood...
G-U-N/UniRL
a unified reinforcement learning toolbox for joint RL on language models and diffusion models