---
title: test
app_file: depthanything_server.py
sdk: gradio
sdk_version: 4.39.0
---
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
[**Lihe Yang**](https://liheyoung.github.io/)
1 · [**Bingyi Kang**](https://scholar.google.com/citations?user=NmHgX-wAAAAJ)
2† · [**Zilong Huang**](http://speedinghzl.github.io/)
2 · [**Xiaogang Xu**](https://xiaogang00.github.io/)
3,4 · [**Jiashi Feng**](https://sites.google.com/site/jshfeng/)
2 · [**Hengshuang Zhao**](https://hszhao.github.io/)
1*
1HKU
2TikTok
3CUHK
4ZJU
†project lead *corresponding author
**CVPR 2024**
This work presents Depth Anything, a highly practical solution for robust monocular depth estimation by training on a combination of 1.5M labeled images and **62M+ unlabeled images**.
![teaser](assets/teaser.png)