{"slug": "depth-pro-2-sharp-and-temporally-consistent-metric-monocular-depth", "title": "Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth", "summary": "Apple researchers released Depth Pro 2, a single scalable network that estimates dense metric depth for images and video at native resolution, and published code and weights at apple-aiml-research.github.io/ml-depth-pro-2/. The paper, arXiv 2611.26603, reports that Depth Pro 2 outperforms prior work on metric accuracy, boundary sharpness and temporal consistency simultaneously, defining a new Pareto frontier across those dimensions and runtime. The work targets the trade-off in which multi-frame methods favor temporal consistency while single-frame methods favor sharpness, with 10 models on Hugging Face already citing the paper.", "body_md": "[Depth Estimation •  Updated     •  76](https://huggingface.co/apple/DepthPro2)  \n\n[Papers](https://huggingface.co/papers)\n\n# Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth\n\n## Abstract\n\nA single scalable network estimates dense metric depth for images and video at native resolution, jointly improving metric accuracy, boundary sharpness, and temporal consistency.\n\n[deepseek-ai/DeepSeek-V4.1-Flash](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash)\n\nWe present Depth Pro 2, an approach to estimating [dense metric depth](https://huggingface.co/papers?q=dense%20metric%20depth) for images and video at full resolution. By analyzing prior methods for [monocular depth estimation](https://huggingface.co/papers?q=monocular%20depth%20estimation), we find that they commonly trade off [temporal consistency](https://huggingface.co/papers?q=temporal%20consistency) and [boundary sharpness](https://huggingface.co/papers?q=boundary%20sharpness): [multi-frame methods](https://huggingface.co/papers?q=multi-frame%20methods) favor consistency, [single-frame methods](https://huggingface.co/papers?q=single-frame%20methods) favor sharpness. To overcome this trade-off, we train a single, [scalable network](https://huggingface.co/papers?q=scalable%20network) that processes both images and video and predicts [depth maps](https://huggingface.co/papers?q=depth%20maps) at [native resolution](https://huggingface.co/papers?q=native%20resolution). Depth Pro 2 produces [depth maps](https://huggingface.co/papers?q=depth%20maps) 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](https://huggingface.co/papers?q=Pareto%20frontier) in terms of [metric accuracy](https://huggingface.co/papers?q=metric%20accuracy), sharpness, [temporal consistency](https://huggingface.co/papers?q=temporal%20consistency), and runtime. We release code and weights at https://apple-aiml-research.github.io/ml-depth-pro-2/\n\n### Community\n\nDepth Pro 2 estimates the depth of every pixel, in meters, from images taken with an ordinary camera. One network handles a single photo, a whole video, or a live camera feed, at the input's full resolution. Its depth is sharp at object edges and steady from frame to frame.\n\nGet this paper in your agent:\n\n`hf papers read 2611.26603` ## Don't have the latest CLI?\n\n`curl -LsSf https://hf.co/cli/install.sh | bash` ## Models citing this paper 10\n\n    [Depth Estimation •  23.5M • Updated   •  42  •  14](https://huggingface.co/apple/DepthPro2-focal)  \n\n#### apple/DepthPro2-focal\n\n[Browse 10 models citing this paper](https://huggingface.co/models?other=arxiv:2611.26603)\n\n## Datasets citing this paper 0\n\nNo dataset linking this paper\n\n### Spaces citing this paper 3\n\n## Collections including this paper 0\n\nNo Collection including this paper\n\n[collection](https://huggingface.co/new-collection)to link it from this page.", "url": "https://wpnews.pro/news/depth-pro-2-sharp-and-temporally-consistent-metric-monocular-depth", "canonical_source": "https://huggingface.co/papers/2611.26603", "published_at": "2026-11-20 16:25:25+00:00", "updated_at": "2026-11-20 16:46:47.236589+00:00", "lang": "en", "topics": ["computer-vision", "ai-research", "machine-learning", "artificial-intelligence"], "entities": ["Apple", "Depth Pro 2", "apple/DepthPro2-focal", "Hugging Face", "arXiv 2611.26603"], "also_reported_by": [], "takeaway": "A single network now predicts metric depth at native resolution for both single images and video, removing the choice between multi-frame temporal consistency and single-frame boundary sharpness.", "recommendation": null, "alternates": {"html": "https://wpnews.pro/news/depth-pro-2-sharp-and-temporally-consistent-metric-monocular-depth", "markdown": "https://wpnews.pro/news/depth-pro-2-sharp-and-temporally-consistent-metric-monocular-depth.md", "text": "https://wpnews.pro/news/depth-pro-2-sharp-and-temporally-consistent-metric-monocular-depth.txt", "jsonld": "https://wpnews.pro/news/depth-pro-2-sharp-and-temporally-consistent-metric-monocular-depth.jsonld"}}