Research map / Image generation / Super-resolution
Learning to Super Resolve Intensity Images From Events
Check 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 |
|---|---|---|---|
| reconstruct super-resolved images directly from events rather than using EV followed by SISR or MISR | Ours · ESIM, 2× | PSNR: 11.309 -> 16.420 | Helped |
| reconstruct super-resolved images directly from events rather than using EV followed by SISR or MISR | Ours · ESIM, 2× | SSIM: 0.385 -> 0.600 | Helped |
| reconstruct super-resolved images directly from events rather than using EV followed by SISR or MISR | Ours · ESIM, 4× | LPIPS: 0.396 -> 0.253 | Helped |
| use the proposed method instead of the strongest baseline | Ours · Real-world sequences, average | SSIM: 0.62 -> 0.64 | Helped |
| use the proposed method instead of the strongest baseline | Ours · Real-world sequences, average | LPIPS: 0.41 -> 0.33 | Helped |
| use seven event stacks instead of three (ablation) | Ours · ESIM, 4× | PSNR: 15.03 -> 16.06 | Helped |
| use seven event stacks instead of three (ablation) | Ours · ESIM, 4× | SSIM: 0.528 -> 0.560 | Helped |
| use L1 loss only instead of combined L1 + LPIPS loss (ablation) | Ours · ESIM, 4×, 3S | PSNR: 15.03 -> 15.33 | Helped |
| use L1 loss only instead of combined L1 + LPIPS loss (ablation) | Ours · ESIM, 4×, 3S | SSIM: 0.528 -> 0.517 | Hurt |
| use LPIPS loss only instead of combined L1 + LPIPS loss (ablation) | Ours · ESIM, 4×, 3S | PSNR: 15.03 -> 10.06 | Hurt |
| use LPIPS loss only instead of combined L1 + LPIPS loss (ablation) | Ours · ESIM, 4×, 3S | LPIPS: 0.258 -> 0.232 | Helped |
| add optical-flow features from FNet (ablation) | Ours · ESIM, 4×, 3S | PSNR: 14.97 -> 15.33 | Helped |
Closest papers by meaning
- EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning (CVPR 2020 · similarity 0.90)
- Turning Frequency to Resolution: Video Super-Resolution via Event Cameras (CVPR 2021 · similarity 0.90)
- EvSTVSR: Event Guided Space-Time Video Super-Resolution (AAAI 2025 · similarity 0.87)
- Event Fields: Capturing Light Fields at High Speed, Resolution, and Dynamic Range (CVPR 2025 · similarity 0.87)
- EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events (CVPR 2025 · similarity 0.86)
- Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · similarity 0.86)
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.