Research map / 3D vision / Depth and stereo
Data Association between Event Streams and Intensity Frames under Diverse Baselines
Dehao Zhang, Qiankun Ding, Peiqi Duan, Chu Zhou, Boxin Shi
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 SDense-Net (ablation) | Full model · Pose, synthetic ScanNet | AUC@20deg: 25.42 -> 39.68 | Improved |
| add SDense-Net (ablation) | Full model · Pose, synthetic ScanNet | AUC@5deg: 2.33 -> 10.40 | Improved |
| use 2 Transformer layers in LSparse-Net instead of 1 (ablation) | Full model · Pose, synthetic ScanNet | AUC@20deg: 32.53 -> 39.68 | Improved |
| add dense output layer (ablation) | Full model · Indoor Flying Split 2 | mean depth error (cm): 45.5 -> 31.8 | Improved |
| add dense output layer (ablation) | Full model · Indoor Flying Split 2 | one pixel accuracy (%): 40.8 -> 50.3 | Improved |
| add SDense-Net (ablation) | Full model · Indoor Flying Split 2 | mean depth error (cm): 37.7 -> 31.8 | Improved |
| add SDense-Net (ablation) | Full model · Indoor Flying Split 2 | one pixel accuracy (%): 43.4 -> 50.3 | Improved |
| use Transformer dimension 512 instead of 256 (ablation) | Full model · Indoor Flying Split 2 | mean depth error (cm): 32.4 -> 31.8 | Improved |
| use Transformer dimension 512 instead of 256 (ablation) | Full model · Indoor Flying Split 2 | one pixel accuracy (%): 47.3 -> 50.3 | Improved |
Closest papers by meaning
- Match-Any-Events: Zero-Shot Motion-Robust Feature Matching Across Wide Baselines for Event Cameras (ECCV 2026 · similarity 0.88)
- Deep Event Stereo Leveraged by Event-to-Image Translation (AAAI 2021 · similarity 0.88)
- Depth Any Event Stream: Enhancing Event-based Monocular Depth Estimation via Dense-to-Sparse Distillation (ICCV 2025 · similarity 0.88)
- EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching (ICCV 2025 · similarity 0.88)
- Event-Driven Dynamic Scene Depth Completion (NeurIPS 2025 · similarity 0.86)
- DERD-Net: Learning Depth from Event-based Ray Densities (NeurIPS 2025 · similarity 0.85)
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.
