Research map / Label-efficient and robust learning / Recognition and long-tail
PCW-Net: Pyramid Combination and Warping Cost Volume for Stereo Matching
Zhelun Shen, Yuchao Dai, Xibin Song, Zhibo Rao, Dingfu Zhou, Liangjun Zhang
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 fusion blocks to the multi-scale cost volume fusion module (ablation) | PCW-Net · KITTI 2015 (KITTI only) | D1_all (%): 2.09 -> 1.97 | Improved |
| use combination volume instead of concatenation volume only (ablation) | PCW-Net · KITTI 2015 (KITTI only) | D1_all (%): 2.04 -> 1.97 | Improved |
| use combination volume instead of group-wise correlation only (ablation) | PCW-Net · KITTI 2015 (KITTI only) | D1_all (%): 2.13 -> 1.97 | Improved |
| add normalization layer C_r to the combination volume (ablation) | PCW-Net · KITTI 2015 (KITTI only) | D1_all (%): 2.14 -> 1.97 | Improved |
| add 3D warping volume V_w as refinement input (ablation) | PCW-Net · KITTI 2015 (KITTI only) | D1_all (%): 2.26 -> 1.97 | Improved |
| add reconstruction error E_rec as refinement input (ablation) | PCW-Net · KITTI 2015 (KITTI only) | D1_all (%): 2.05 -> 1.97 | Improved |
| add left features and initial disparity as refinement inputs (ablation) | PCW-Net · KITTI 2015 (KITTI only) | D1_all (%): 1.99 -> 1.97 | Improved |
| add WVBDF refinement on top of MSCVF (ablation) | PCW-Net · KITTI 2015 train, trained on Scene Flow | D1_all (%): 5.81 -> 5.55 | Improved |
| add WVBDF refinement on top of MSCVF (ablation) | PCW-Net · Scene Flow test | EPE (px): 0.8387 -> 0.7868 | Improved |
| add MSCVF module (ablation) | PCW-Net without WVBDF · KITTI 2015 train, trained on Scene Flow | D1_all (%): 6.18 -> 5.81 | Improved |
| add multi-scale cost volume fusion to raw disparity (ablation) | PCW-Net · ETH3D (Scene Flow trained) | bad 1.0 (%): 16.44 -> 9.96 | Improved |
| add stacked hourglass after MSCVF (ablation) | PCW-Net · KITTI 2012 (Scene Flow trained) | D1_all (%): 5.62 -> 4.49 | Improved |
Later papers that compared with this method
1 later accepted paper reports PCWNet as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- Robust Synthetic-to-Real Transfer for Stereo Matching (CVPR 2024 · better on 2 of 4 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CFNet — CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching (CVPR 2021) · better on 4 of 4 shared results
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
- CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching (CVPR 2021 · similarity 0.91)
- Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy (TPAMI 2019 · similarity 0.91)
- Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches (JMLR 2016 · similarity 0.91)
- On the confidence of stereo matching in a deep-learning era: a quantitative evaluation (TPAMI 2021 · similarity 0.90)
- Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching (CVPR 2020 · similarity 0.90)
- AANet: Adaptive Aggregation Network for Efficient Stereo Matching (CVPR 2020 · similarity 0.90)
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.
