Research map / Video / Video segmentation and tracking
EvIntSR-Net: Event Guided Multiple Latent Frames Reconstruction and Super-Resolution
Jin Han, Yixin Yang, Chu Zhou, Chao Xu, Boxin Shi
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 |
|---|---|---|---|
| add LFR-Net for latent frame reconstruction (ablation) | EvIntSR-Net · Synthetic test set (ablation) | PSNR: 22.97 -> 23.12 | Improved |
| add LFR-Net for latent frame reconstruction (ablation) | EvIntSR-Net · Synthetic test set (ablation) | SSIM: 0.769 -> 0.776 | Improved |
| add LFR-Net for latent frame reconstruction (ablation) | EvIntSR-Net · Synthetic test set (ablation) | LPIPS: 0.134 -> 0.130 | Improved |
| add deformable convolution alignment (ablation) | EvIntSR-Net · Synthetic test set (ablation) | PSNR: 23.08 -> 23.12 | Improved |
| add deformable convolution alignment (ablation) | EvIntSR-Net · Synthetic test set (ablation) | SSIM: 0.774 -> 0.776 | Improved |
| add deformable convolution alignment (ablation) | EvIntSR-Net · Synthetic test set (ablation) | LPIPS: 0.131 -> 0.130 | Improved |
| add feedback block (recurrent fusion) (ablation) | EvIntSR-Net · Synthetic test set (ablation) | PSNR: 23.08 -> 23.12 | Improved |
| add feedback block (recurrent fusion) (ablation) | EvIntSR-Net · Synthetic test set (ablation) | SSIM: 0.766 -> 0.776 | Improved |
| add feedback block (recurrent fusion) (ablation) | EvIntSR-Net · Synthetic test set (ablation) | LPIPS: 0.151 -> 0.130 | Improved |
| event-guided latent frame fusion (EvIntSR-Net) instead of multi-frame APS-only SR | APS+MISR · Synthetic test set (2x SR) | PSNR: 15.69 -> 23.12 | Improved |
| event-guided latent frame fusion (EvIntSR-Net) instead of multi-frame APS-only SR | APS+MISR · Synthetic test set (4x SR) | PSNR: 15.18 -> 23.25 | Improved |
Closest papers by meaning
- E2SRI: Learning to Super-Resolve Intensity Images From Events (TPAMI 2021 · similarity 0.92)
- Learning to Super Resolve Intensity Images From Events (CVPR 2020 · similarity 0.92)
- Joint Framework for Single Image Reconstruction and Super-Resolution With an Event Camera (TPAMI 2021 · similarity 0.91)
- EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning (CVPR 2020 · similarity 0.90)
- EvSTVSR: Event Guided Space-Time Video Super-Resolution (AAAI 2025 · similarity 0.89)
- EvEnhancer: Empowering Effectiveness, Efficiency and Generalizability for Continuous Space-Time Video Super-Resolution with Events (CVPR 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.
