Research map / Video / Video segmentation and tracking
Temporal Event Stereo via Joint Learning with Stereoscopic Flow
Hoonhee Cho, Jae-Young Kang, 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 feature warping via stereoscopic flow (ablation) | single-frame event stereo · MVSEC split 1 | mean depth error (cm): 15.2 -> 14.7 | Improved |
| add cost volume warping on top of feature warping (ablation) | temporal event stereo · MVSEC split 1 | mean depth error (cm): 14.7 -> 13.6 | Improved |
| use both feature and cost volume warping (ablation) | temporal event stereo · MVSEC split 1 | mean depth error (cm): 15.2 -> 13.0 | Improved |
| use entropy reliability filter instead of addition for cost fusion (ablation) | cost volume fusion · MVSEC split 1 | mean depth error (cm): 14.0 -> 13.0 | Improved |
| share stereo features in a lightweight flow network instead of separate EV-Flow (ablation) | stereoscopic flow network · MVSEC split 1 | mean depth error (cm): 13.7 -> 13.0 | Improved |
| use hard epipolar constraint (shared vertical flow) instead of soft (ablation) | stereoscopic flow · MVSEC split 1 | mean depth error (cm): 13.3 -> 13.0 | Improved |
| use temporal disparity consistency loss instead of contrast maximization only (ablation) | flow loss · MVSEC split 1 | mean depth error (cm): 13.6 -> 13.1 | Improved |
| add contrast loss to TDC loss (ablation) | flow loss · MVSEC split 1 | mean depth error (cm): 13.1 -> 13.0 | Improved |
| increase voxel grid bins from 1 to 5 (ablation) | temporal event stereo · MVSEC split 1 | mean depth error (cm): 13.7 -> 13.0 | Improved |
| increase voxel grid bins from 5 to 10 (ablation) | temporal event stereo · MVSEC split 1 | mean depth error (cm): 13.0 -> 13.7 | Hurt |
| use more frames at test time (streaming) than the 4 used in training (ablation) | temporal event stereo · MVSEC split 1 | mean depth error (cm): 13.0 -> 12.8 | Improved |
| replace recurrent temporal aggregation with flow-based warping | DTC-SPADE · MVSEC inference cost | FPS: 11.6 -> 71.6 | Improved |
Closest papers by meaning
- Temporal Stereo Matching From Event Cameras via Joint Learning With Stereoscopic Flow (TPAMI 2025 · similarity 0.98)
- EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching (ICCV 2025 · similarity 0.93)
- Learning an Event Sequence Embedding for Dense Event-Based Deep Stereo (ICCV 2019 · similarity 0.93)
- Discrete Time Convolution for Fast Event-Based Stereo (CVPR 2022 · similarity 0.92)
- Active Event-based Stereo Vision (CVPR 2025 · similarity 0.91)
- Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain (NeurIPS 2024 · similarity 0.89)
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.
