This work presents Depth Anything V2. It significantly outperforms V1 in fine-grained details and robustness. Compared with SD-based models, it enjoys faster inference speed, fewer parameters, and higher depth accuracy.

• 2024-06-20: Our repository and project page are flagged by GitHub and removed from the public for 6 days. Sorry for the inconvenience.
• 2024-06-14: Paper, project page, code, models, demo, and benchmark are all released.

We provide four models of varying scales for robust relative depth estimation:

import cv2
import torch

from depth_anything_v2.dpt import DepthAnythingV2

# take depth-anything-v2-large as an example
model = DepthAnythingV2(encoder='vitl', features=256, out_channels=[256, 512, 1024, 1024])
model.load_state_dict(torch.load('checkpoints/depth_anything_v2_vitl.pth', map_location='cpu'))
model.eval()

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

git clone https://github.com/DepthAnything/Depth-Anything-V2
cd Depth-Anything-V2
pip install -r requirements.txt

python run.py --encoder <vits | vitb | vitl> --img-path <path> --outdir <outdir> [--input-size <size>] [--pred-only] [--grayscale]

Options:

• --img-path: You can either 1) point it to an image directory storing all interested images, 2) point it to a single image, or 3) point it to a text file storing all image paths.
• --input-size (optional): By default, we use input size 518 for model inference. You can increase the size for even more fine-grained results.
• --pred-only (optional): Only save the predicted depth map, without raw image.
• --grayscale (optional): Save the grayscale depth map, without applying color palette.

For example:

python run.py --encoder vitl --img-path assets/examples --outdir depth_vis

If you want to use Depth Anything V2 on videos:

python run_video.py --encoder <vits | vitb | vitl> --video-path assets/examples_video --outdir video_depth_vis [--input-size <size>] [--pred-only] [--grayscale]

Please note that our larger model has better temporal consistency on videos.

To use our gradio demo locally:

python app.py

You can also try our online demo.

Note: Compared to V1, we have made a minor modification to the DINOv2-DPT architecture (originating from this issue). In V1, we unintentionally used features from the last four layers of DINOv2 for decoding. In V2, we use intermediate features instead. Although this modification did not improve details or accuracy, we decided to follow this common practice.

Please refer to metric depth estimation.

Please refer to DA-2K benchmark.

We sincerely appreciate all the community support for our Depth Anything series. Thank you a lot!

• Depth Anything V2 TensorRT: https://github.com/spacewalk01/depth-anything-tensorrt
• Depth Anything V2 in ComfyUI: https://github.com/kijai/ComfyUI-DepthAnythingV2
• Depth Anything V2 in Android:
  • https://github.com/shubham0204/Depth-Anything-Android
  • https://github.com/FeiGeChuanShu/ncnn-android-depth_anything

Depth-Anything-V2-Small model is under the Apache-2.0 license. Depth-Anything-V2-Base/Large/Giant models are under the CC-BY-NC-4.0 license.

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}
}