# Depth-Anything-3
**Repository Path**: magicor/Depth-Anything-3
## Basic Information
- **Project Name**: Depth-Anything-3
- **Description**: https://github.com/ByteDance-Seed/Depth-Anything-3.git
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-12-05
- **Last Updated**: 2025-12-05
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
Depth Anything 3: Recovering the Visual Space from Any Views
[**Haotong Lin**](https://haotongl.github.io/)
* · [**Sili Chen**](https://github.com/SiliChen321)
* · [**Jun Hao Liew**](https://liewjunhao.github.io/)
* · [**Donny Y. Chen**](https://donydchen.github.io)
* · [**Zhenyu Li**](https://zhyever.github.io/) · [**Guang Shi**](https://scholar.google.com/citations?user=MjXxWbUAAAAJ&hl=en) · [**Jiashi Feng**](https://scholar.google.com.sg/citations?user=Q8iay0gAAAAJ&hl=en)
[**Bingyi Kang**](https://bingykang.github.io/)
*†
†project lead *Equal Contribution
This work presents **Depth Anything 3 (DA3)**, a model that predicts spatially consistent geometry from
arbitrary visual inputs, with or without known camera poses.
In pursuit of minimal modeling, DA3 yields two key insights:
- 💎 A **single plain transformer** (e.g., vanilla DINO encoder) is sufficient as a backbone without architectural specialization,
- ✨ A singular **depth-ray representation** obviates the need for complex multi-task learning.
🏆 DA3 significantly outperforms
[DA2](https://github.com/DepthAnything/Depth-Anything-V2) for monocular depth estimation,
and [VGGT](https://github.com/facebookresearch/vggt) for multi-view depth estimation and pose estimation.
All models are trained exclusively on **public academic datasets**.