Research map / Detection and segmentation / CNN features
Event-Image Fusion Stereo Using Cross-Modality Feature Propagation
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 |
|---|---|---|---|
| Fuse events and intensity images with the proposed SMC-Net | Stereo disparity estimation on MVSEC · MVSEC split 1 | mean disparity error [pix]: 0.53 -> 0.37 | Helped |
| Fuse events and intensity images with the proposed SMC-Net | Stereo disparity estimation on MVSEC · MVSEC split 3 | mean disparity error [pix]: 0.64 -> 0.52 | Helped |
| Fuse events and RGB images with the proposed SMC-Net | Stereo disparity estimation · Synthetic test set | mean disparity error [pix]: 0.88 -> 0.82 | Helped |
| Add the sparse disparity branch during training (ablation) | SMC-Net · MVSEC split 1 | mean disparity error [pix]: 0.40 -> 0.37 | Helped |
| Add the sparse disparity branch during training (ablation) | SMC-Net · MVSEC split 3 | mean disparity error [pix]: 0.53 -> 0.52 | Helped |
| Add the sparse disparity branch during training (ablation) | SMC-Net · Synthetic test set | mean disparity error [pix]: 0.84 -> 0.82 | Helped |
| Use EIAT fusion instead of concatenation (ablation) | SMC-Net · MVSEC split 1 | mean disparity error [pix]: 0.43 -> 0.40 | Helped |
| Use EIAT fusion instead of concatenation (ablation) | SMC-Net · MVSEC split 3 | mean disparity error [pix]: 0.53 -> 0.53 | No clear effect |
| Use EIAT fusion instead of SPADE (ablation) | SMC-Net · MVSEC split 1 | mean disparity error [pix]: 0.42 -> 0.40 | Helped |
| Use EIAT fusion instead of SPADE (ablation) | SMC-Net · MVSEC split 3 | mean disparity error [pix]: 0.51 -> 0.53 | No clear effect |
| Use spatial multi-scale correlation rather than PSMNet correlation architecture (ablation) | SMC-Net · MVSEC split 1 | mean disparity error [pix]: 0.42 -> 0.40 | Helped |
| Use spatial multi-scale correlation rather than PSMNet correlation architecture (ablation) | SMC-Net · MVSEC split 3 | mean disparity error [pix]: 0.59 -> 0.53 | Helped |
Closest papers by meaning
- DERD-Net: Learning Depth from Event-based Ray Densities (NeurIPS 2025 · similarity 0.88)
- Active Event-based Stereo Vision (CVPR 2025 · similarity 0.88)
- Event-Driven Dynamic Scene Depth Completion (NeurIPS 2025 · similarity 0.87)
- Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain (NeurIPS 2024 · similarity 0.86)
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.85)
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events (AAAI 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.