DepthCrafter

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

<div align="center"> <img src='https://depthcrafter.github.io/img/logo.png' style="height:140px"></img> <a href='https://arxiv.org/abs/2409.02095'><img src='https://img.shields.io/badge/arXiv-2409.02095-b31b1b.svg'></a> &nbsp;<a href='https://depthcrafter.github.io'><img src='https://img.shields.io/badge/Project-Page-Green'></a> &nbsp;

Wenbo Hu^{1* †}, Xiangjun Gao^2*, Xiaoyu Li^{1* †}, Sijie Zhao¹, Xiaodong Cun¹, <br> Yong Zhang¹, Long Quan², Ying Shan^{3, 1} <br><br> ¹Tencent AI Lab ²The Hong Kong University of Science and Technology ³ARC Lab, Tencent PCG

arXiv preprint, 2024

</div>

If you find DepthCrafter useful, please help ⭐ the </a> <a style='font-size:18px;color: #FF5DB0' href='https://github.com/Tencent/DepthCrafter'>[Github Repo]</a>, which is important to Open-Source projects. Thanks!

🔆 Introduction

🤗 DepthCrafter can generate temporally consistent long depth sequences with fine-grained details for open-world videos, without requiring additional information such as camera poses or optical flow.

🎥 Visualization

We provide some demos of unprojected point cloud sequences, with reference RGB and estimated depth videos. Please refer to our project page for more details. <img src="./assets/visualization.gif">