Research map / Architectures and efficiency / CNN design
Discrete Time Convolution for Fast Event-Based Stereo
Kaixuan Zhang, Kaiwei Che, Jianguo Zhang, Jie Cheng, Ziyang Zhang, Qinghai Guo, Luziwei Leng
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 |
|---|---|---|---|
| add channel-wise discrete temporal dynamics to event encoding | event-based stereo matching · MVSEC split 1 | MDE [cm]: 16.9±1.0 -> 15.4±0.1 | Improved |
| add channel-wise discrete temporal dynamics to event encoding | event-based stereo matching · MVSEC split 1 | 1PA [%]: 89.3±1.4 -> 91.2±0.1 | Improved |
| add the SPADE dual path using edge information from original event frames (ablation) | DTC-PDS · MVSEC split 1 | Mean depth error [cm]: 15.3 -> 13.5 | Improved |
| add the SPADE dual path using edge information from original event frames (ablation) | DTC-PDS · MVSEC split 3 | Mean depth error [cm]: 18.6 -> 17.1 | Improved |
| add the SPADE dual path using edge information from original event frames (ablation) | DTC-PDS · DSEC | 1PE: 9.517 -> 9.27 | Improved |
| add the SPADE dual path using edge information from original event frames (ablation) | DTC-PDS · DSEC | 2PE: 2.356 -> 2.405 | Hurt |
| add the SPADE dual path using edge information from original event frames (ablation) | DTC-PDS · DSEC | MAE: 0.527 -> 0.526 | Improved |
| add the SPADE dual path using edge information from original event frames (ablation) | DTC-PDS · DSEC | RMSE: 1.264 -> 1.285 | Hurt |
| use the faster DTC-PDS architecture instead of DTC-SPADE (ablation) | streaming event-based stereo · MVSEC streaming | FPS: 64 -> 110 | Improved |
| use CTC rather than DTC for temporal event encoding (ablation) | event-based stereo matching · MVSEC split 1 | MDE [cm]: 15.4±0.1 -> 15.1±0.3 | No clear effect |
Closest papers by meaning
- Temporal Event Stereo via Joint Learning with Stereoscopic Flow (ECCV 2024 · similarity 0.92)
- Learning an Event Sequence Embedding for Dense Event-Based Deep Stereo (ICCV 2019 · similarity 0.91)
- Temporal Stereo Matching From Event Cameras via Joint Learning With Stereoscopic Flow (TPAMI 2025 · similarity 0.91)
- Active Event-based Stereo Vision (CVPR 2025 · similarity 0.87)
- Event-Driven Dynamic Scene Depth Completion (NeurIPS 2025 · similarity 0.87)
- DERD-Net: Learning Depth from Event-based Ray Densities (NeurIPS 2025 · 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.
