|
--- |
|
license: apache-2.0 |
|
library_name: DepthAnyVideo |
|
arxiv: 2410.10815 |
|
tags: |
|
- vision |
|
pipeline_tag: depth-estimation |
|
widget: |
|
- inference: false |
|
--- |
|
|
|
## **Depth Any Video with Scalable Synthetic Data** |
|
|
|
<div align="center"> |
|
<a href='https://depthanyvideo.github.io'><img src='https://img.shields.io/badge/Project-Page-Green'></a> |
|
|
|
_**[Honghui Yang<sup>*</sup>](https://hhyangcs.github.io), |
|
[Di Huang<sup>*</sup>](https://dihuang.me), |
|
[Wei Yin](https://scholar.google.com/citations?user=ZIf_rtcAAAAJ), |
|
[Chunhua Shen](https://scholar.google.com/citations?user=Ljk2BvIAAAAJ), |
|
[Haifeng Liu](https://scholar.google.com/citations?user=oW108fUAAAAJ), <br> |
|
[Xiaofei He](https://scholar.google.com/citations?user=QLLFowsAAAAJ), |
|
[Binbin Lin<sup>†</sup>](https://scholar.google.com/citations?user=Zmvq4KYAAAAJ), |
|
[Wanli Ouyang](https://scholar.google.com/citations?user=pw_0Z_UAAAAJ), |
|
[Tong He<sup>†</sup>](https://scholar.google.com/citations?user=kWADCMUAAAAJ)**_ |
|
<br><br> |
|
Shanghai AI Laboratory, |
|
Zhejiang University, |
|
The University of Sydney |
|
|
|
arXiv preprint, 2024 |
|
|
|
</div> |
|
|
|
<img src="./assets/visualization.gif"> |
