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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add edge-aware smoothness loss (ablation) | baseline disparity network · KITTI 2012 val | 3-pixel error: 2.844 -> 2.555 | Improved |
| add edge features on top of smoothness loss (ablation) | baseline with smoothness loss · KITTI 2012 val | 3-pixel error: 2.555 -> 2.385 | Improved |
| add edge cues (feature plus smoothness loss) (ablation) | baseline disparity network · FlyingThings3D test | 3-pixel error: 4.443 -> 3.940 | Improved |
| use edge-aware smoothness instead of Charbonnier (ablation) | EdgeStereo · KITTI 2012 val | 3-pixel error: 2.852 -> 2.385 | Improved |
| use edge-aware smoothness instead of second-order gradient (ablation) | EdgeStereo · KITTI 2012 val | 3-pixel error: 2.816 -> 2.385 | Improved |
| add residual pyramid RP_4 (ablation) | EdgeStereo · KITTI 2012 val | 3-pixel error: 2.484 -> 2.289 | Improved |
| use residual pyramid instead of cascaded refinement network (ablation) | EdgeStereo · KITTI 2012 val | 3-pixel error: 2.407 -> 2.289 | Improved |
| increase smoothness intensity beta from 0 to 2 (ablation) | EdgeStereo · KITTI 2012 val | 3-pixel error: 2.569 -> 2.289 | Improved |
| increase beta from 2 to 8 (ablation) | EdgeStereo · KITTI 2012 val | 3-pixel error: 2.289 -> 2.341 | Hurt |
| multi-task learning with stereo branch (ablation) | edge branch · BSDS500 test | ODS F-measure: 0.340 -> 0.460 | Improved |
| add edge cues (ablation) | baseline · Middlebury val (half) | 2-pixel error: 12.473 -> 11.540 | Improved |
| add edge cues, KITTI 2012 reflective regions (ablation) | baseline · KITTI 2012 test reflective regions | 3-pixel error: 8.53 -> 5.84 | Improved |
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.
- HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching (CVPR 2021 · better on 1 of 1 shared result)
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
- Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches (JMLR 2016 · similarity 0.91)
- Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy (TPAMI 2019 · similarity 0.91)
- On the confidence of stereo matching in a deep-learning era: a quantitative evaluation (TPAMI 2021 · similarity 0.90)
- StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction (ECCV 2018 · similarity 0.90)
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching (ICML 2024 · similarity 0.89)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.88)
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.
