Research map / Video / Video segmentation and tracking
Learning to Super-Resolve Blurry Images With Events
Lei Yu, Bishan Wang, Xiang Zhang, Haijian Zhang, Wen Tao Yang, Jianzhuang Liu, Gui-Song Xia
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 dual sparse learning (DSL) without RESM (ablation) | eSL-Net · GoPro synthetic events (sequence) | PSNR: 23.80 -> 24.12 | Improved |
| add DSL without RESM (ablation) | eSL-Net · HQF real events (sequence) | PSNR: 22.16 -> 22.43 | Improved |
| add DSL with RESM present (ablation) | eSL-Net++ · GoPro synthetic events (sequence) | PSNR: 24.42 -> 24.69 | Improved |
| add DSL with RESM present (ablation) | eSL-Net++ · HQF real events (sequence) | PSNR: 22.86 -> 22.99 | Improved |
| add rigorous event shuffle-and-merge (RESM) without DSL (ablation) | eSL-Net · GoPro synthetic events (sequence) | PSNR: 23.80 -> 24.42 | Improved |
| add RESM with DSL present (ablation) | eSL-Net++ · GoPro synthetic events (sequence) | PSNR: 24.12 -> 24.69 | Improved |
| add RESM without DSL (ablation) | eSL-Net · HQF real events (sequence) | PSNR: 22.16 -> 22.86 | Improved |
| increase recursion blocks from 5 to 15 (ablation) | eSL-Net++ · GoPro synthetic events (single frame) | PSNR: 25.13 dB -> 25.73 dB | Improved |
| increase recursion blocks from 15 to 25 (ablation) | eSL-Net++ · GoPro synthetic events (single frame) | PSNR: 25.73 dB -> 25.78 dB | No clear effect |
| add DSL and dual sparse event denoising (eSL-Net to eSL-Net++) | eSL-Net · GoPro synthetic events (single frame) | PSNR: 25.32 -> 25.73 | Improved |
| use events with unified SR and deblurring instead of image-only cascades | eSL-Net++ · GoPro synthetic events (single frame) | PSNR: 22.86 -> 25.73 | Improved |
| unified joint E-SRB network instead of two-stage Deblur-then-SR with event deblurring | eSL-Net++ · GoPro synthetic events (single frame) | PSNR: 23.75 -> 25.73 | Improved |
Closest papers by meaning
- Event Enhanced High-Quality Image Recovery (ECCV 2020 · similarity 0.91)
- Event-Guided Super-Resolving Blurry Image via Asymmetric Integral Driven Consistency (AAAI 2026 · similarity 0.89)
- Exploiting Blurry Representations for Event-guided Video Super-Resolution (AAAI 2026 · similarity 0.89)
- Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · similarity 0.88)
- Joint Framework for Single Image Reconstruction and Super-Resolution With an Event Camera (TPAMI 2021 · similarity 0.88)
- Generalizing Event-Based Motion Deblurring in Real-World Scenarios (ICCV 2023 · 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.
