Research map / 3D vision / Depth and stereo
EDNet: Efficient Disparity Estimation With Cost Volume Combination and Attention-Based Spatial Residual
Songyan Zhang, Zhicheng Wang, Qiang Wang, Jinshuo Zhang, Gang Wei, Xiaowen Chu
Check 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 |
|---|---|---|---|
| combine correlation and squeezed concatenation volumes (ablation) | EDNet · Scene Flow | EPE: 1.07 -> 1.00 | Improved |
| add the squeezed concatenation volume to correlation-only matching (ablation) | EDNet · Scene Flow | EPE: 1.67 -> 1.63 | Improved |
| add the correlation volume to squeezed-concatenation-only matching (ablation) | EDNet · Scene Flow | EPE: 1.89 -> 1.63 | Improved |
| add residual learning (ablation) | EDNet with combined volume · Scene Flow | EPE: 1.63 -> 1.04 | Improved |
| use attention-based rather than normal residual learning (ablation) | EDNet · Scene Flow | EPE: 1.04 -> 1.00 | Improved |
| provide error maps at multiple corresponding scales (ablation) | EDNet residual module · Scene Flow | EPE | Improved |
| use EDNet rather than AANet+ | Scene Flow · Scene Flow | EPE: 0.72 -> 0.63 | Improved |
| use EDNet rather than GANet | KITTI 2015 · KITTI 2015 | inference time (s): 0.36 -> 0.05 | Improved |
| use EDNet rather than GANet | KITTI runtime comparison · KITTI runtime comparison | memory (GB): 6.53 -> 2.52 | Improved |
| use EDNet rather than GANet | KITTI runtime comparison · KITTI runtime comparison | GFLOPs: 1936.98 -> 162.92 | Improved |
| use EDNet rather than AANet | KITTI 2012 · KITTI 2012 | Out All (%): 3.60 -> 3.67 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- StereoNet — StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction (ECCV 2018) · better on 0 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
- StereoDRNet: Dilated Residual StereoNet (CVPR 2019 · similarity 0.88)
- End-To-End Learning of Geometry and Context for Deep Stereo Regression (ICCV 2017 · similarity 0.88)
- Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation (AAAI 2023 · similarity 0.87)
- A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation (CVPR 2016 · similarity 0.87)
- Learning Depth with Convolutional Spatial Propagation Network (TPAMI 2019 · similarity 0.87)
- Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation (CVPR 2020 · similarity 0.87)
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.
