AI Paper Atlas

Research map / 3D vision / Depth and stereo

EdgeStereo: An Effective Multi-task Learning Network for Stereo Matching and Edge Detection

Xiao Song, Xu Zhao, Liangji Fang, Hanwen Hu, Yizhou Yu

IJCV 2020 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 205 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
add edge-aware smoothness loss (ablation)baseline disparity network · KITTI 2012 val3-pixel error: 2.844 -> 2.555Improved
add edge features on top of smoothness loss (ablation)baseline with smoothness loss · KITTI 2012 val3-pixel error: 2.555 -> 2.385Improved
add edge cues (feature plus smoothness loss) (ablation)baseline disparity network · FlyingThings3D test3-pixel error: 4.443 -> 3.940Improved
use edge-aware smoothness instead of Charbonnier (ablation)EdgeStereo · KITTI 2012 val3-pixel error: 2.852 -> 2.385Improved
use edge-aware smoothness instead of second-order gradient (ablation)EdgeStereo · KITTI 2012 val3-pixel error: 2.816 -> 2.385Improved
add residual pyramid RP_4 (ablation)EdgeStereo · KITTI 2012 val3-pixel error: 2.484 -> 2.289Improved
use residual pyramid instead of cascaded refinement network (ablation)EdgeStereo · KITTI 2012 val3-pixel error: 2.407 -> 2.289Improved
increase smoothness intensity beta from 0 to 2 (ablation)EdgeStereo · KITTI 2012 val3-pixel error: 2.569 -> 2.289Improved
increase beta from 2 to 8 (ablation)EdgeStereo · KITTI 2012 val3-pixel error: 2.289 -> 2.341Hurt
multi-task learning with stereo branch (ablation)edge branch · BSDS500 testODS F-measure: 0.340 -> 0.460Improved
add edge cues (ablation)baseline · Middlebury val (half)2-pixel error: 12.473 -> 11.540Improved
add edge cues, KITTI 2012 reflective regions (ablation)baseline · KITTI 2012 test reflective regions3-pixel error: 8.53 -> 5.84Improved

Later papers that compared with this method

1 later accepted paper reports EdgeStereo as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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