Hnabil
/

depth-pro

Hnabil commited on Oct 6

Commit

a92f9d9

•

1 Parent(s): 39e1b9b

Update README.md

Files changed (1) hide show

README.md CHANGED Viewed

@@ -9,7 +9,7 @@ This software project accompanies the research paper:
 **[Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://arxiv.org/abs/2410.02073)**,
 *Aleksei Bochkovskii, Amaël Delaunoy, Hugo Germain, Marcel Santos, Yichao Zhou, Stephan R. Richter, and Vladlen Koltun*.
-![](data/depth-pro-teaser.jpg)
 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.

 **[Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://arxiv.org/abs/2410.02073)**,
 *Aleksei Bochkovskii, Amaël Delaunoy, Hugo Germain, Marcel Santos, Yichao Zhou, Stephan R. Richter, and Vladlen Koltun*.
+![](https://cdn-uploads.huggingface.co/production/uploads/6437ed1fa1fa778a4da872a9/zjyBNH8bLuc2V93wOR0Ks.jpeg)
 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.