Depth Pro: Sharp Monocular Metric Depth in Less Than a Second

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 & weights at https://github.com/apple/ml-depth-pro I N T R O D U C T I O N Zero-shot monocular depth estimation underpins a growing variety of applications, such as advanced image editing, view synthesis, and conditional image generation. Inspired by MiDaS (Ranftl et al., 2022) and many follow-up works (Ranftl et al., 2021; Ke et al., 2024; Yang et al., 2024a; Piccinelli et al., 2024; Hu et al., 2024), applications increasingly leverage the ability to derive a dense pixelwise depth map for any image. Our work is motivated in particular by novel view synthesis from a single image, an exciting application that has been transformed by advances in monocular depth estimation (