Research map / Vision-language and multimodal / Cross-modal learning
Synthetic Aperture Imaging With Events and Frames
Wei Liao, Xiang Zhang, Lei Yu, Shijie Lin, Wen Yang, Ning Qiao
Check 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 |
|---|---|---|---|
| Fuse events and frames with EF-SAI-Net | SAI · Dense Occlusions, Indoor | PSNR: 31.0715 -> 30.5387 | Mixed |
| Fuse events and frames with EF-SAI-Net | SAI · Dense Occlusions, Outdoor | PSNR: 20.2579 -> 19.7834 | Hurt |
| Fuse events and frames with EF-SAI-Net | SAI · Sparse Occlusions, Indoor | PSNR: 31.0529 -> 35.0089 | Improved |
| Fuse events and frames with EF-SAI-Net | SAI · Sparse Occlusions, Outdoor | PSNR: 15.3313 -> 21.0394 | Improved |
| Add CME for cross-modal feature enhancement (ablation) | EF-SAI-Net · Dense and sparse occlusions, Indoor | PSNR: 29.9534 -> 30.5387; 34.4912 -> 35.0089 | Improved |
| Add DAF for density-aware feature selection (ablation) | EF-SAI-Net · Dense and sparse occlusions, Indoor | PSNR: 29.9625 -> 30.5387; 34.9402 -> 35.0089 | Improved |
| Add Iref (ablation) | EF-SAI-Net · Dense and sparse occlusions, Indoor | PSNR: 27.9170 -> 30.5387; 33.0011 -> 35.0089 | Improved |
| Add Eref (ablation) | EF-SAI-Net · Dense and sparse occlusions, Indoor | PSNR: 29.1839 -> 30.5387; 29.6165 -> 35.0089 | Improved |
| Add Iref E→F (ablation) | EF-SAI-Net · Dense and sparse occlusions, Indoor | PSNR: 23.9406 -> 30.5387; 25.1331 -> 35.0089 | Improved |
| Use all three multi-modal signals (ablation) | EF-SAI-Net · Sparse Occlusions, Outdoor | PSNR: 21.3782 -> 21.0394 | No clear effect |
Closest papers by meaning
- Event-Based Synthetic Aperture Imaging With a Hybrid Network (CVPR 2021 · similarity 0.92)
- REDIR: Refocus-free Event-based De-occlusion Image Reconstruction (ECCV 2024 · similarity 0.91)
- Learning to See Through With Events (TPAMI 2022 · similarity 0.90)
- Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow (CVPR 2025 · similarity 0.82)
- Time-Efficient Light-Field Acquisition Using Coded Aperture and Events (CVPR 2024 · similarity 0.82)
- EvFocus: Learning to Reconstruct Sharp Images from Out-of-Focus Event Streams (ICML 2025 · similarity 0.82)
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.
