Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation

About

We release MiDaS v3.1 for monocular depth estimation, offering a variety of new models based on different encoder backbones. This release is motivated by the success of transformers in computer vision, with a large variety of pretrained vision transformers now available. We explore how using the most promising vision transformers as image encoders impacts depth estimation quality and runtime of the MiDaS architecture. Our investigation also includes recent convolutional approaches that achieve comparable quality to vision transformers in image classification tasks. While the previous release MiDaS v3.0 solely leverages the vanilla vision transformer ViT, MiDaS v3.1 offers additional models based on BEiT, Swin, SwinV2, Next-ViT and LeViT. These models offer different performance-runtime tradeoffs. The best model improves the depth estimation quality by 28% while efficient models enable downstream tasks requiring high frame rates. We also describe the general process for integrating new backbones. A video summarizing the work can be found at https://youtu.be/UjaeNNFf9sE and the code is available at https://github.com/isl-org/MiDaS.

Reiner Birkl, Diana Wofk, Matthias M\"uller• 2023

Related benchmarks

TaskDatasetResultRank
Monocular Depth EstimationNYU v2 (test)
Abs Rel0.048
320
Monocular Depth EstimationKITTI--
220
Monocular Depth EstimationNYU V2
Delta 1 Acc98
174
Monocular Depth EstimationETH3D
AbsRel6.1
159
Depth EstimationKITTI--
156
Monocular Depth EstimationDIODE
AbsRel26.2
147
Monocular Depth EstimationSintel
Abs Rel0.342
127
Monocular Depth EstimationCityscapes
Accuracy (delta < 1.25)74.3
74
Monocular Depth EstimationETH-3D (test)
A.Rel0.139
49
Depth EstimationDIODE (test)
AbsRel0.075
33
Showing 10 of 31 rows

Other info

Code

Follow for update