Depth Anything V2 Small

🚀 Depth-Anything-V2-Small

Depth-Anything-V2-Small is a powerful monocular depth estimation model trained with a large amount of synthetic and real-world data, offering high - performance depth estimation capabilities.

🚀 Quick Start

Depth Anything V2 is trained from 595K synthetic labeled images and 62M+ real unlabeled images. It provides the most capable monocular depth estimation (MDE) model with the following features:

• more fine-grained details than Depth Anything V1
• more robust than Depth Anything V1 and SD-based models (e.g., Marigold, Geowizard)
• more efficient (10x faster) and more lightweight than SD-based models
• impressive fine-tuned performance with our pre-trained models

✨ Features

• Fine - grained Details: Offers more fine - grained details compared to Depth Anything V1.
• Robustness: More robust than Depth Anything V1 and SD - based models like Marigold and Geowizard.
• Efficiency: 10x faster and more lightweight than SD - based models.
• Fine - tuned Performance: Demonstrates impressive fine - tuned performance with pre - trained models.

📦 Installation

git clone https://huggingface.co/spaces/depth-anything/Depth-Anything-V2
cd Depth-Anything-V2
pip install -r requirements.txt

💻 Usage Examples

Basic Usage

Download the model first and put it under the checkpoints directory.

import cv2
import torch

from depth_anything_v2.dpt import DepthAnythingV2

model = DepthAnythingV2(encoder='vits', features=64, out_channels=[48, 96, 192, 384])
model.load_state_dict(torch.load('checkpoints/depth_anything_v2_vits.pth', map_location='cpu'))
model.eval()

raw_img = cv2.imread('your/image/path')
depth = model.infer_image(raw_img) # HxW raw depth map

📄 License

This project is licensed under the Apache - 2.0 license.

📚 Documentation

If you find this project useful, please consider citing:

@article{depth_anything_v2,
  title={Depth Anything V2},
  author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Zhao, Zhen and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
  journal={arXiv:2406.09414},
  year={2024}
}

@inproceedings{depth_anything_v1,
  title={Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data}, 
  author={Yang, Lihe and Kang, Bingyi and Huang, Zilong and Xu, Xiaogang and Feng, Jiashi and Zhao, Hengshuang},
  booktitle={CVPR},
  year={2024}
}