Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
By Alexey Bochkovskiy, Amaël Delaunoy, Hugo Germain, Marcel Santos, Yichao Zhou, Stephan R. Richter, Vladlen Koltun. arXiv.org, 2024
514 citations recorded by the source corpus.
We present a foundation model for zero-shot metric monocular depth estimation. Our model, Depth Pro, synthesizes high-resolution depth maps with unparalleled sharpness and high-frequency details. The predictions are metric, with absolute scale, without relying on the availability of metadata such as camera intrinsics. And the model is fast, producing a 2.25-megapixel depth map in 0.3 seconds on a standard GPU. These characteristics are enabled by a number of technical contributions, including an efficient multi-scale vision transformer for dense prediction, a training protocol that combines real and synthetic datasets to achieve high metric accuracy alongside fine boundary tracing, dedicated evaluation metrics for boundary accuracy in estimated depth maps, and state-of-the-art focal length estimation from a single image. Extensive experiments analyze specific design choices and demonstrate that Depth Pro outperforms prior work along multiple dimensions. We release code and weights at https://github.com/apple/ml-depth-pro
Subfields: Computer Graphics and Computer-Aided Design, Industrial and Manufacturing Engineering, Mechanical Engineering
View Paper: https://www.semanticscholar.org/paper/44fe1c6263aa3b87b95be6bfba2ef03c79d550a6
Citations in the corpus
- Depth Anything 3: Recovering the Visual Space from Any Views (2025, unknown): “Modern generalist approaches [6, 42, 95, 112, 113, 118] exemplify this trend by leveraging massive multi-dataset training and advanced architectures like vision transformers [67] or DiT [64].”
- Continuous 3D Perception Model with Persistent State (2025, unknown): “While depth maps provide valuable 3D information, converting them into 3D point clouds typically requires camera intrinsics [8, 32, 55], with camera extrinsics often left unmodeled.”
- Qwen-Image Technical Report (2025, unknown): “Second, to evaluate the model’s spatial understanding and generative capability in 3D vision tasks, we benchmark its performance on novel view synthesis (Downs et al., 2022) and depth estimation (Bochkovskii et al., 2024).”