README.md

---
license: other
license_name: license
license_link: LICENSE
---


<div align="center">
<h2>StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos</h2>

Sijie Zhao*&emsp;
Wenbo Hu*&emsp;
Xiaodong Cun*&emsp;
Yong Zhang&dagger;&emsp;
Xiaoyu Li&dagger;&emsp;<br>
Zhe Kong&emsp;
Xiangjun Gao&emsp;
Muyao Niu&emsp;
Ying Shan

&emsp;* equal contribution &emsp; &dagger; corresponding author 

<h3>Tencent AI Lab&emsp;&emsp;ARC Lab, Tencent PCG</h3>

<a href='https://arxiv.org/abs/2409.07447'><img src='https://img.shields.io/badge/arXiv-PDF-a92225'></a> &emsp;
<a href='https://stereocrafter.github.io/'><img src='https://img.shields.io/badge/Project_Page-Page-64fefe' alt='Project Page'></a> &emsp;
<a href='https://huggingface.co/TencentARC/StereoCrafter'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Weights-yellow'></a>
</div>

## Introduction

We propose a novel framework to convert any 2D videos to immersive stereoscopic 3D ones that can be viewed on different display devices, like 3D Glasses, Apple Vision Pro and 3D Display. It can be applied to various video sources, such as movies, vlogs, 3D cartoons, and AIGC videos.

![teaser](assets/teaser.jpg)