Research map / Architectures and efficiency / Neural architecture search
EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching
Qiang Wang, Shaohuai Shi, Kaiyong Zhao, Xiaowen Chu
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 progressive shrinking on scale and refinement stages (ablation) | EASNet-S (K=3,W=2,D=2,S=2) · Scene Flow test | EPE (px): 1.8 -> 0.86 | Improved |
| add progressive shrinking over kernel, width and depth (ablation) | EASNet sub-networks · Scene Flow test | EPE (px) | Improved |
| add progressive shrinking on scale and refinement beyond K-W-D (ablation) | EASNet small sub-networks · Scene Flow test | EPE (px): nearly 50% error reduction | Improved |
| add progressive shrinking when shrinking width and depth (ablation) | EASNet sub-networks · Scene Flow test | EPE (px) | Improved |
| increase scale from S=2 to S=4 (ablation) | EASNet sub-network · Scene Flow test | EPE (px) | No clear effect |
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.
- AANet — AANet: Adaptive Aggregation Network for Efficient Stereo Matching (CVPR 2020) · 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
- AANet: Adaptive Aggregation Network for Efficient Stereo Matching (CVPR 2020 · similarity 0.91)
- Hierarchical Neural Architecture Search for Deep Stereo Matching (NeurIPS 2020 · similarity 0.91)
- CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching (CVPR 2021 · similarity 0.89)
- GA-Net: Guided Aggregation Net for End-To-End Stereo Matching (CVPR 2019 · similarity 0.89)
- Revisiting Non-Parametric Matching Cost Volumes for Robust and Generalizable Stereo Matching (NeurIPS 2022 · similarity 0.89)
- IINet: Implicit Intra-inter Information Fusion for Real-Time 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.
