Research map / 3D vision / Depth and stereo
Deep Event Stereo Leveraged by Event-to-Image Translation
Read the paperCheck 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 |
|---|---|---|---|
| add reconstructed image features and stacked dilated SPADE aggregation to event features | DDES · MVSEC Indoor Flying, dense disparity splits 1 and 3 | mean depth error [cm]: 16.6 -> 14.2; 23.5 -> 19.4 | Helped |
| add reconstructed image features and stacked dilated SPADE aggregation to event features | DDES · MVSEC Indoor Flying, dense disparity splits 1 and 3 | one-pixel accuracy [%]: 89.8 -> 92.1; 82.5 -> 89.6 | Helped |
| add event-to-image reconstruction and feature guidance | DDES · MVSEC Indoor Flying, sparse disparity splits 1 and 3 | mean depth error [cm]: 13.6 -> 11.3; 18.4 -> 15.2 | Helped |
| add event-to-image reconstruction and feature guidance | DDES · MVSEC Indoor Flying split 1, sparse disparity | mean disparity error [pix]: 0.54 -> 0.49 | Helped |
| add reconstructed-image guidance through a reconstruction sub-network (ablation) | DDES · MVSEC split 1 ablation | mean depth error [cm]: 13.6 -> 11.8 | Helped |
| add feature aggregation sub-network (ablation) | event-to-image reconstruction model · MVSEC split 1 ablation | mean depth error [cm]: 11.8 -> 11.7 | Helped |
| add stacked dilated convolution to the feature aggregation sub-network (ablation) | proposed event stereo network · MVSEC split 1 ablation | mean depth error [cm]: 11.7 -> 11.3 | Helped |
| add spatial context attention (ablation) | image reconstruction sub-network · MVSEC split 1 ablation | mean depth error [cm]: 12.4 -> 11.3 | Helped |
| add cross-semantic attention (ablation) | image reconstruction sub-network · MVSEC split 1 ablation | mean depth error [cm]: 12.2 -> 11.3 | Helped |
| add explicit reconstruction loss (ablation) | reconstruction sub-network as a feature extractor · MVSEC split 1 sparse disparity | mean depth error [cm]: 12.9 vs 11.3 | Helped |
| use the event stereo matching sub-network rather than PSMNet (ablation) | proposed event stereo architecture · MVSEC split 1 sparse disparity | mean depth error [cm]: 12.2 vs 11.3 | 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)
- LaSe-E2V: Towards Language-guided Semantic-aware Event-to-Video Reconstruction (NeurIPS 2024 · similarity 0.87)
- E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning (AAAI 2024 · 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.