titleDepth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth
authorsPeiyun Hu, Marko Mihajlovic, Lyndon Duong, Lahav Lipson, Wei Dong, Amaël Delaunoy, Stephan R. Richter, Vladlen Koltun
date2026-11-19
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.26603
affiliationApple
upvotes28 (Hugging Face Daily Papers, 2026-11-21)
linksabs pdf hf code
cite
relatedOpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory
It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning
MintAct: A Unified Visual Agent for Digital Environments
FastFrames: Video Generation at Interactive Latency
Decoding Looped Transformers Better for (Almost) Free
abstractWe present Depth Pro 2, an approach to estimating dense metric depth for images and video at full resolution. By analyzing prior methods for monocular depth estimation, we find that they commonly trade off temporal consistency and boundary sharpness: multi-frame methods favor consistency, single-frame methods favor sharpness. To overcome this trade-off, we train a single, scalable network that processes both images and video and predicts depth maps at native resolution. Depth Pro 2 produces depth maps that are metrically accurate, sharp, and temporally consistent all at once, outperforming prior work in all of these dimensions. We release a family of models that define a new Pareto frontier in terms of metric accuracy, sharpness, temporal consistency, and runtime. We release code and weights at https://apple-aiml-research.github.io/ml-depth-pro-2/

bibtex

@misc{hu2026depth,
  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 Amaël Delaunoy and Stephan R. Richter and Vladlen Koltun},
  year={2026},
  eprint={2611.26603},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2611.26603}
}