Research map / 3D vision / Depth and stereo
BANet: Bilateral Aggregation Network for Mobile Stereo Matching
Gangwei Xu, Jiaxin Liu, Xianqi Wang, Junda Cheng, Yong Deng, Jinliang Zang, Yurui Chen, Xin Yang
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 bilateral aggregation to 2D aggregation (ablation) | BANet-2D baseline · Scene Flow test | EPE (px): 0.63 -> 0.59 | Improved |
| add scale-aware spatial attention to bilateral aggregation (2D) (ablation) | BANet-2D · Scene Flow test | EPE (px): 0.59 -> 0.57 | Improved |
| add bilateral aggregation to 2D aggregation (ablation) | BANet-2D baseline · Scene Flow test | Bad 3.0 (%): 2.75 -> 2.57 | Improved |
| add bilateral aggregation to 3D aggregation (ablation) | BANet-3D baseline · Scene Flow test | EPE (px): 0.56 -> 0.53 | Improved |
| add scale-aware spatial attention to bilateral aggregation (3D) (ablation) | BANet-3D · Scene Flow test | EPE (px): 0.53 -> 0.51 | Improved |
| add bilateral aggregation to 2D aggregation (ablation) | BANet-2D baseline · Scene Flow test | MACs (G): 29 -> 38 | Hurt |
| add bilateral aggregation to 2D aggregation (ablation) | BANet-2D baseline · KITTI 2015 test | D1-fg (%): 3.67 -> 3.03 | Improved |
| add bilateral aggregation to 3D aggregation (ablation) | BANet-3D baseline · KITTI 2015 test | D1-fg (%): 3.87 -> 3.02 | Improved |
| add bilateral aggregation to 2D aggregation (ablation) | BANet-2D baseline · KITTI 2012 reflective | 3-noc (%): 8.81 -> 5.59 | Improved |
| add bilateral aggregation to 3D aggregation (ablation) | BANet-3D baseline · KITTI 2012 reflective | 3-noc (%): 6.10 -> 5.37 | Improved |
| plug bilateral aggregation into PSMNet | PSMNet · Scene Flow test (plug-in BA) | EPE (px): 1.09 -> 0.77 | Improved |
| plug bilateral aggregation into GwcNet | GwcNet · Scene Flow test (plug-in BA) | EPE (px): 0.76 -> 0.67 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PSMNet — PSMNet: Position-Aware Stereo Merging Network for Room Layout Estimation (CVPR 2022) · better on 1 of 1 shared result
- StereoNet — StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction (ECCV 2018) · 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
- AANet: Adaptive Aggregation Network for Efficient Stereo Matching (CVPR 2020 · similarity 0.89)
- Practical Stereo Matching via Cascaded Recurrent Network With Adaptive Correlation (CVPR 2022 · similarity 0.87)
- Accurate and Efficient Stereo Matching via Attention Concatenation Volume (TPAMI 2023 · similarity 0.87)
- A Survey on Deep Stereo Matching in the Twenties (IJCV 2025 · similarity 0.87)
- CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching (CVPR 2021 · similarity 0.87)
- EdgeStereo: An Effective Multi-task Learning Network for Stereo Matching and Edge Detection (IJCV 2020 · similarity 0.86)
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.
