Research map / Vision-language and multimodal / Cross-modal learning
Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereo
Ninghui Xu, Fabio Tosi, Lihui Wang, Jiawei Han, Luca Bartolomei, Zhiting Yao, Matteo Poggi, Stefano Mattoccia
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 CDEA and SCC together (ablation) | imgCMPStereo · DSEC test (All sequences) | MAE: 0.594 -> 0.565 | Improved |
| add CDEA (ablation) | imgCMPStereo · DSEC test (All sequences) | MAE: 0.583 -> 0.565 | Improved |
| add SCC (ablation) | imgCMPStereo · DSEC test (All sequences) | MAE: 0.589 -> 0.565 | Improved |
| add cascaded multi-scale refinement (ablation) | imgCMPStereo · DSEC test (All sequences) | MAE: 0.588 -> 0.565 | Improved |
| add CDEA (ablation) | imgCMPStereo · DSEC test (All sequences) | 2PE: 2.968 -> 2.790 | Improved |
| add SCC (ablation) | imgCMPStereo · DSEC test (All sequences) | 2PE: 2.945 -> 2.790 | Improved |
| add cascaded multi-scale refinement (ablation) | imgCMPStereo · DSEC test (All sequences) | 1PE: 11.927 -> 11.432 | Improved |
| add CDEA (ablation) | Bi-CMPStereo · DSEC test (All sequences) | MAE: 0.546 -> 0.532 | Improved |
| add SCC (ablation) | Bi-CMPStereo · DSEC test (All sequences) | MAE: 0.551 -> 0.532 | Improved |
| add SCC (ablation) | Bi-CMPStereo · DSEC test (All sequences) | 1PE: 11.290 -> 10.613 | Improved |
| add HVT context learning (ablation) | Bi-CMPStereo · MVSEC (generalization from DSEC, All) | MAE: 2.093 -> 1.858 | Improved |
| add HVT context learning (ablation) | Bi-CMPStereo · MVSEC (generalization from DSEC, All) | 2PE: 36.005 -> 32.121 | Improved |
Closest papers by meaning
- Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain (NeurIPS 2024 · similarity 0.88)
- Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching (ECCV 2024 · similarity 0.87)
- CrossOver: 3D Scene Cross-Modal Alignment (CVPR 2025 · similarity 0.85)
- PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching (NeurIPS 2025 · similarity 0.85)
- Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data (ICLR 2024 · similarity 0.84)
- EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition (CVPR 2024 · similarity 0.84)
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.
