Research map / 3D vision / Depth and stereo
Learning an Event Sequence Embedding for Dense Event-Based Deep Stereo
Stepan Tulyakov, Francois Fleuret, Martin Kiefel, Peter Gehler, Michael Hirsch
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 |
|---|---|---|---|
| replace hand-crafted temporal aggregation with a continuous fully-connected layer (ablation) | DDES · Indoor Flying split 1 | mean depth error (cm): 16.5 -> 13.6 | Improved |
| replace hand-crafted temporal aggregation with a continuous fully-connected layer (ablation) | DDES · Indoor Flying split 1 | one-pixel accuracy (%): 87.3 -> 91.3 | Improved |
| use continuous fully-connected layer instead of temporal convolutional network (ablation) | DDES · Indoor Flying split 1 | mean depth error (cm): 13.8 -> 13.6 | Improved |
| use continuous fully-connected layer instead of temporal convolutional network (ablation) | DDES · Indoor Flying split 1 | one-pixel accuracy (%): 90.7 -> 91.3 | Improved |
| train on dense ground truth instead of sparse ground truth | DDES · Indoor Flying split 1 | mean depth error (cm): 13.6 -> 16.7 | Hurt |
| train on dense ground truth instead of sparse ground truth | DDES · Indoor Flying split 3 | mean depth error (cm): 18.4 -> 27.8 | Hurt |
| increase event queue capacity from 1 to 7 (shallow network) (ablation) | shallow stereo network · Indoor Flying split 1 validation | mean depth error (cm): 80.4 -> 67.9 | Improved |
| increase event queue capacity from 1 to 15 (deep network) (ablation) | DDES · Indoor Flying split 1 validation | mean depth error (cm): 13.3 -> 13.3 | No clear effect |
| increase event queue capacity from 1 to 7 (deep network) (ablation) | DDES · Indoor Flying split 1 validation | mean depth error (cm): 13.3 -> 13.5 | No clear effect |
Closest papers by meaning
- Deep Event Stereo Leveraged by Event-to-Image Translation (AAAI 2021 · similarity 0.93)
- Temporal Event Stereo via Joint Learning with Stereoscopic Flow (ECCV 2024 · similarity 0.93)
- Discrete Time Convolution for Fast Event-Based Stereo (CVPR 2022 · similarity 0.91)
- Temporal Stereo Matching From Event Cameras via Joint Learning With Stereoscopic Flow (TPAMI 2025 · similarity 0.91)
- A Low Power, High Throughput, Fully Event-Based Stereo System (CVPR 2018 · similarity 0.91)
- Active Event-based Stereo Vision (CVPR 2025 · similarity 0.90)
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.
