AI Paper Atlas

Research map / 3D vision / Depth and stereo

The Midas Touch for Metric Depth

Yu Ma, Zizhan Guo, Zuyi Xiong, Haoran Zhang, Yi Feng, Hongbo Zhao, Hanli Wang, Rui Fan

CVPR 2026 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use inverse-depth proxy instead of least squares in depth domain (ablation)per-segment calibration · KITTIRMSE: 7.013 -> 6.782Improved
use least squares instead of median alignment (ablation)per-segment calibration · KITTIRMSE: 10.891 -> 7.013Improved
add sparse graph optimization instead of global scale recovery (ablation)segment-wise recovery · KITTIRMSE: 2.521 -> 2.232Improved
add sparse graph optimization instead of global scale recovery (ablation)segment-wise recovery · VOIDRMSE: 0.554 -> 0.459Improved
add discontinuity-aware geodesic cost (ablation)dynamic programming refinement · KITTIRMSE: 2.618 -> 2.049Improved
use polynomial basis instead of B-spline (ablation)dynamic programming refinement · KITTIRMSE: 2.112 -> 2.049Improved
increase iterations k from 3 to 5 (ablation)dynamic programming refinement · KITTIRMSE: 2.028 -> 1.913Improved
increase iterations k from 3 to 5 (ablation)dynamic programming refinement · VOIDRMSE: 0.366 -> 0.391Hurt
add MTD to DepthAnythingV2 relative depthDepthAnythingV2 · KITTIAbsRel: 0.080 -> 0.022Improved
add MTD to MiDaS relative depthMiDaS · DIODEAbsRel: 0.266 -> 0.113Improved
add MTD to Droid SLAM instead of LiDAR onlyDroid · KITTI Odometry Seq 06ATE-RMSE: 104.552 -> 12.194Improved
use MTD instead of least-squares alignment on VGGT depthVGGT · Multi-view stereoAbsRel: 0.108 -> 0.054Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy