Research map / Detection and segmentation / CNN features
Semantic Stereo Matching With Pyramid Cost Volumes
Zhenyao Wu, Xinyi Wu, Xiaoping Zhang, Song Wang, Lili Ju
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 semantic branch to single spatial cost volume (ablation) | single-cost-volume stereo net · Scene Flow validation | end-point error: 2.12 -> 1.76 | Improved |
| add semantic branch to single spatial cost volume (ablation) | single-cost-volume stereo net · KITTI 2015 validation | error rate (%): 2.63 -> 2.42 | Improved |
| add joint training of semantic branch (ablation) | semantic branch variant · Scene Flow validation | end-point error: 1.76 -> 1.78 | No clear effect |
| add joint training of semantic branch (ablation) | semantic branch variant · KITTI 2015 validation | error rate (%): 2.42 -> 2.37 | Improved |
| use spatial pyramid cost volumes (ablation) | single-cost-volume stereo net · Scene Flow validation | end-point error: 2.12 -> 1.21 | Improved |
| use spatial pyramid cost volumes (ablation) | single-cost-volume stereo net · KITTI 2015 validation | error rate (%): 2.63 -> 2.11 | Improved |
| add 3D multiple cost volumes (ablation) | pyramid cost volume variant · Scene Flow validation | end-point error: 1.21 -> 1.04 | Improved |
| add 3D multiple cost volumes (ablation) | pyramid cost volume variant · KITTI 2015 validation | error rate (%): 2.11 -> 1.99 | Improved |
| add 3D feature fusion module (FFM) (ablation) | SSPCV-Net · Scene Flow validation | end-point error: 1.07 -> 0.98 | Improved |
| add 3D feature fusion module (FFM) (ablation) | SSPCV-Net · KITTI 2015 validation | error rate (%): 2.10 -> 1.85 | Improved |
| add boundary loss in joint training (ablation) | SSPCV-Net · Scene Flow validation | end-point error: 1.01 -> 0.98 | Improved |
| add boundary loss in joint training (ablation) | SSPCV-Net · KITTI 2015 validation | error rate (%): 1.93 -> 1.85 | Improved |
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.
- SegStereo — SegStereo: Exploiting Semantic Information for Disparity Estimation (ECCV 2018) · better on 3 of 3 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
- Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy (TPAMI 2019 · similarity 0.92)
- Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches (JMLR 2016 · similarity 0.91)
- Unsupervised Learning of Stereo Matching (ICCV 2017 · similarity 0.90)
- Learning for Disparity Estimation Through Feature Constancy (CVPR 2018 · similarity 0.90)
- Hierarchical Neural Architecture Search for Deep Stereo Matching (NeurIPS 2020 · similarity 0.90)
- SemStereo: Semantic-Constrained Stereo Matching Network for Remote Sensing (AAAI 2025 · similarity 0.89)
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.
