Depth Pro 2 estimates sharp, metric, temporally consistent depth for images and video at full resolution.
Video comparisons
2K–4K sources. Videos generated with Depth Pro 2 H+ at native resolution, baselines at their default settings. Inverse depth, with one color range per model for the whole clip.
Image comparisons
Images generated with Depth Pro 2 H+. Each method at its default resolution.
Sharpness versus temporal consistency
Depth Pro 2 outperforms prior work operating on a single frame or multiple frames on sharpness (Boundary F1 score) and temporal consistency (Jitter). Results averaged over Sintel and Spring datasets.
Method
Our depth estimation network consists of a multi-view transformer that ingests one or multiple input frames and processes them jointly, and a DPT decoder, which predicts an inverse depth map per input frame. 1 The transformer shares information across frames: after the first third of its blocks, it alternates attention within each frame and attention across frames. 2 The DPT decoder takes tokens from several transformer blocks, assembles them into feature maps at 1/32 to 1/4 of the input resolution, and decodes them into an inverse depth map per frame.
Citation
@article{DepthPro2:2026:arxiv,
title = {Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth},
author = {Peiyun Hu and Marko Mihajlovic and Lyndon Duong and Lahav Lipson and Wei Dong and Ama\"{e}l Delaunoy and Stephan R. Richter and Vladlen Koltun},
journal = {arXiv:261X.XXXXX},
year = {2026},
url = {https://arxiv.org/abs/261X.XXXXX},
}