README.md

---
license: mit
pipeline_tag: image-to-image
library_name: diffusers
---

# [ICCV 2025] GenStereo: Towards Open-World Generation of Stereo Images and Unsupervised Matching


[![Project Site](https://img.shields.io/badge/Project-Web-green)](https://qjizhi.github.io/genstereo)  [![Spaces](https://img.shields.io/badge/Spaces-Demo-yellow?logo=huggingface)](https://huggingface.co/spaces/FQiao/GenStereo)  [![Github](https://img.shields.io/badge/Github-Repo-orange?logo=github)](https://github.com/Qjizhi/GenStereo)  [![Models](https://img.shields.io/badge/Models-checkpoints-blue?logo=huggingface)](https://huggingface.co/FQiao/GenStereo-sd2.1/tree/main)  [![arXiv](https://img.shields.io/badge/arXiv-2503.12720-red?logo=arxiv)](https://arxiv.org/abs/2503.12720)


This repository contains the model presented in [GenStereo: Towards Open-World Generation of Stereo Images and Unsupervised Matching](https://huggingface.co/papers/2503.12720). The models are finetuned on Stable Diffusion 1.5, for SD v2.1, you can find [here](https://huggingface.co/FQiao/GenStereo-sd2.1).
![](teaser_coco.jpg).