Research map / 3D vision / Depth and stereo
Stereo Depth From Events Cameras: Concentrate and Focus on the Future
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use the proposed event-only concentration and future-knowledge method instead of E-Stereo | event-only stereo depth estimation · DSEC | MAE: 0.529 -> 0.519 | Helped |
| use the proposed event-only concentration and future-knowledge method instead of E-Stereo | event-only stereo depth estimation · DSEC | RMSE: 1.222 -> 1.231 | Hurt |
| fuse concentrated events with intensity images using the proposed method instead of EI-Stereo | event-and-intensity stereo depth estimation · DSEC | MAE: 0.396 -> 0.364 | Helped |
| add mixed-density event stacking (ablation) | stereo matching network · DSEC | MAE: 0.864 -> 0.852 | Helped |
| add the concentration network to mixed-density event stacking (ablation) | stereo matching network with MES · DSEC | MAE: 0.852 -> 0.831 | Helped |
| add training-time future-knowledge transfer using KL divergence (ablation) | stereo matching network with MES and CN · DSEC | MAE: 0.831 -> 0.797 | Helped |
| transfer future knowledge at deformable aggregation rather than feature extraction (ablation) | future-knowledge transfer · DSEC | MAE: 0.810 -> 0.797 | Helped |
| transfer future knowledge at deformable aggregation rather than multiscale refinement (ablation) | future-knowledge transfer · DSEC | MAE: 0.833 -> 0.797 | Helped |
Closest papers by meaning
- DERD-Net: Learning Depth from Event-based Ray Densities (NeurIPS 2025 · similarity 0.91)
- Active Event-based Stereo Vision (CVPR 2025 · similarity 0.90)
- Event-Driven Dynamic Scene Depth Completion (NeurIPS 2025 · similarity 0.88)
- Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain (NeurIPS 2024 · similarity 0.88)
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.86)
- AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scenes (AAAI 2025 · similarity 0.86)
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.