Research map / 3D vision / Depth and stereo
Event-Based Synthetic Aperture Imaging With a Hybrid Network
Xiang Zhang, Wei Liao, Lei Yu, Wen Yang, Gui-Song Xia
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 |
|---|---|---|---|
| Use event-camera data instead of frame-based captures | SAI · Dense Occlusion Indoor | PSNR (dB): 13.89 -> 14.71 | Improved |
| Use event-camera data instead of frame-based captures | SAI · Extreme Exposure Over | Entropy: 4.855 -> 5.706 | Improved |
| Use event-camera data instead of frame-based captures | SAI · Extreme Exposure Under | STD: 26.06 -> 50.10 | Improved |
| Add CNN reconstruction to F-SAI | F-SAI · Dense Occlusion Indoor | PSNR (dB): 13.89 -> 26.44 | Improved |
| Add CNN reconstruction to F-SAI | F-SAI · Extreme Exposure Under | Entropy: 5.022 -> 4.165 | Hurt |
| Replace event accumulation with CNN reconstruction | E-SAI · Dense Occlusion Indoor | PSNR (dB): 14.71 -> 31.27 | Improved |
| Replace event accumulation with CNN reconstruction | E-SAI · Dense Occlusion Outdoor | SSIM: 0.1887 -> 0.5237 | Improved |
| Replace event accumulation with CNN reconstruction | E-SAI · Extreme Exposure Over | Entropy: 5.706 -> 6.921 | Improved |
| Replace the three-layer CNN encoder with an SNN encoder (ablation) | E-SAI+CNN · Dense Occlusion Outdoor | PSNR (dB): 17.62 -> 24.02 | Improved |
| Replace the three-layer CNN encoder with an SNN encoder (ablation) | E-SAI+CNN · Dense Occlusion Outdoor | SSIM: 0.5237 -> 0.6524 | Improved |
| Replace the three-layer CNN encoder with an SNN encoder (ablation) | E-SAI+CNN · Dense Occlusion Indoor | PSNR (dB): 31.27 -> 33.04 | Improved |
| Replace the three-layer CNN encoder with an SNN encoder (ablation) | E-SAI+CNN · Extreme Exposure Over | Entropy: 6.921 -> 7.417 | Improved |
Closest papers by meaning
- Learning to See Through With Events (TPAMI 2022 · similarity 0.96)
- Synthetic Aperture Imaging With Events and Frames (CVPR 2022 · similarity 0.92)
- REDIR: Refocus-free Event-based De-occlusion Image Reconstruction (ECCV 2024 · similarity 0.88)
- EvIntSR-Net: Event Guided Multiple Latent Frames Reconstruction and Super-Resolution (ICCV 2021 · similarity 0.84)
- EvFocus: Learning to Reconstruct Sharp Images from Out-of-Focus Event Streams (ICML 2025 · similarity 0.83)
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.83)
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.
