Research map / 3D vision / Depth and stereo
Selection and Cross Similarity for Event-Image Deep Stereo
Hoonhee Cho, Kuk-Jin Yoon
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 differentiable event selection (DES) (ablation) | GwcNet-g baseline · MVSEC Split 1 | mean disparity error: 0.4020 -> 0.4111 | Hurt |
| add differentiable event selection (DES) (ablation) | GwcNet-g baseline · MVSEC Split 3 | mean disparity error: 0.4358 -> 0.4153 | Improved |
| add differentiable event selection (DES) (ablation) | GwcNet-g baseline · MVSEC Split 3 | one-pixel accuracy: 91.7874 -> 93.7863 | Improved |
| add differentiable event selection (DES) (ablation) | GwcNet-g baseline · MVSEC Split 3 | mean depth error: 16.5391 -> 14.3000 | Improved |
| add neighbor cross similarity feature (NCSF) (ablation) | GwcNet-g baseline · MVSEC Split 1 | mean disparity error: 0.4020 -> 0.3909 | Improved |
| add neighbor cross similarity feature (NCSF) (ablation) | GwcNet-g baseline · MVSEC Split 3 | one-pixel accuracy: 91.7874 -> 93.0166 | Improved |
| add NCSF on top of DES (ablation) | GwcNet-g + DES · MVSEC Split 3 | mean disparity error: 0.4153 -> 0.3895 | Improved |
| add DES on top of NCSF (ablation) | GwcNet-g + NCSF · MVSEC Split 1 | mean disparity error: 0.3909 -> 0.3776 | Improved |
| select K=3 of B=5 event bins instead of K=1 (ablation) | Proposed · MVSEC Split 1 | one-pixel accuracy: 91.6541 -> 94.7201 | Improved |
| select K=3 of B=5 event bins instead of all 5 (ablation) | Proposed · MVSEC Split 1 | one-pixel accuracy: 94.1027 -> 94.7201 | Improved |
| select K=3 instead of K=2 (ablation) | Proposed · MVSEC Split 1 | one-pixel accuracy: 93.2581 -> 94.7201 | Improved |
| full method vs EIS event-image fusion | Proposed · MVSEC Split 3 | one-pixel accuracy: 88.1 -> 94.0 | Improved |
Closest papers by meaning
- Event-Image Fusion Stereo Using Cross-Modality Feature Propagation (AAAI 2022 · similarity 0.93)
- Event-Intensity Stereo: Estimating Depth by the Best of Both Worlds (ICCV 2021 · similarity 0.92)
- Active Event-based Stereo Vision (CVPR 2025 · similarity 0.89)
- Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain (NeurIPS 2024 · similarity 0.89)
- Event-Driven Dynamic Scene Depth Completion (NeurIPS 2025 · similarity 0.88)
- DERD-Net: Learning Depth from Event-based Ray Densities (NeurIPS 2025 · 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.
