lucataco / depth-anything-video

Depth Anything on full video files

  • Public
  • 289 runs
  • GitHub
  • Paper
  • License



Run time and cost

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 4 minutes. The predict time for this model varies significantly based on the inputs.


Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

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.


Features of Depth Anything

  • Relative depth estimation:

    Our foundation models listed here can provide relative depth estimation for any given image robustly.

  • Metric depth estimation

    We fine-tune our Depth Anything model with metric depth information from NYUv2 or KITTI. It offers strong capabilities of both in-domain and zero-shot metric depth estimation.

  • Better depth-conditioned ControlNet

    We re-train a better depth-conditioned ControlNet based on Depth Anything. It offers more precise synthesis than the previous MiDaS-based ControlNet.

  • Downstream high-level scene understanding

    The Depth Anything encoder can be fine-tuned to downstream high-level perception tasks, e.g., semantic segmentation, 86.2 mIoU on Cityscapes and 59.4 mIoU on ADE20K.


If you find this project useful, please consider citing:

      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},