Research map / Image generation / Super-resolution
E2SRI: Learning to Super-Resolve Intensity Images From Events
Mohammad Mostafavi, Yeongwoo Nam, Jonghyun Choi, Kuk‐Jin Yoon
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 |
|---|---|---|---|
| use combined L1 + LPIPS loss instead of L1 only (ablation) | E2SRI 4x 3S · ESIM simulated | LPIPS: 0.485 -> 0.258 | Improved |
| use combined L1 + LPIPS loss instead of L1 only (ablation) | E2SRI 4x 3S · ESIM simulated | SSIM: 0.517 -> 0.528 | Improved |
| use combined L1 + LPIPS loss instead of L1 only (ablation) | E2SRI 4x 3S · ESIM simulated | PSNR: 15.33 -> 15.03 | Hurt |
| use combined L1 + LPIPS loss instead of LPIPS only (ablation) | E2SRI 4x 3S · ESIM simulated | PSNR: 10.06 -> 15.03 | Improved |
| use combined L1 + LPIPS loss instead of LPIPS only (ablation) | E2SRI 4x 3S · ESIM simulated | LPIPS: 0.232 -> 0.258 | Hurt |
| add optical flow network FNet (ablation) | E2SRI 4x 3S L1 · ESIM simulated | PSNR: 14.97 -> 15.33 | Improved |
| add optical flow network FNet (ablation) | E2SRI 4x 3S L1 · ESIM simulated | LPIPS: 0.499 -> 0.485 | Improved |
| use 7 stacks instead of 3 stacks (ablation) | E2SRI 2x · ESIM simulated | PSNR: 15.46 -> 16.42 | Improved |
| use 7 stacks instead of 3 stacks (ablation) | E2SRI 4x · ESIM simulated | PSNR: 15.03 -> 16.06 | Improved |
| use 7 stacks instead of 3 stacks (ablation) | E2SRI 2x · ESIM simulated | MSE: 0.323 -> 0.108 | Improved |
| direct event-to-SR reconstruction instead of EV followed by MISR | E2SRI 2x · ESIM simulated | PSNR: 11.309 -> 16.420 | Improved |
| direct event-to-SR reconstruction instead of EV followed by SISR | E2SRI 4x · ESIM simulated | LPIPS: 0.543 -> 0.253 | Improved |
Closest papers by meaning
- Learning to Super Resolve Intensity Images From Events (CVPR 2020 · similarity 0.98)
- Joint Framework for Single Image Reconstruction and Super-Resolution With an Event Camera (TPAMI 2021 · similarity 0.94)
- EvIntSR-Net: Event Guided Multiple Latent Frames Reconstruction and Super-Resolution (ICCV 2021 · similarity 0.92)
- EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning (CVPR 2020 · similarity 0.91)
- High Speed and High Dynamic Range Video with an Event Camera (TPAMI 2019 · similarity 0.90)
- EvSTVSR: Event Guided Space-Time Video Super-Resolution (AAAI 2025 · similarity 0.87)
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.
