Research map / Image generation / Super-resolution
Event-Guided Scene Text Image Super-Resolution
Zihan Qi, Zeyu Xiao, Haoyi Zhao, Yang Zhao, Feng Xue, Wei Jia
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 DSFB to baseline (ablation) | EvTSR baseline · TextZoom (CRNN) | average accuracy: 50.8% -> 56.4% | Improved |
| add CMF to baseline (ablation) | EvTSR baseline · TextZoom (CRNN) | average accuracy: 50.8% -> 56.5% | Improved |
| add CMF on top of DSFB (ablation) | EvTSR · TextZoom (CRNN) | average accuracy: 56.4% -> 57.5% | Improved |
| use dynamic convolution instead of standard 1x1 convolution in DSFB (ablation) | DSFB · TextZoom (CRNN) | average accuracy: 52.2% -> 57.5% | Improved |
| add event-guided high-frequency (EGH) branch (ablation) | DSFB · TextZoom (CRNN) | average accuracy: 53.4% -> 57.5% | Improved |
| add text-guided low-frequency (TGL) branch (ablation) | DSFB · TextZoom (CRNN) | average accuracy: 54.3% -> 57.5% | Improved |
| use dynamic kernel instead of 1x1 convolution in CMF (ablation) | CMF · TextZoom (CRNN) | average accuracy: 52.5% -> 57.5% | Improved |
| use concatenation instead of element-wise summation in CMF (ablation) | CMF · TextZoom (CRNN) | average accuracy: 55.3% -> 57.5% | Improved |
| use concatenation plus dynamic kernel instead of sum plus 1x1 conv (ablation) | CMF · TextZoom (CRNN) | average accuracy: 51.7% -> 57.5% | Improved |
| add event data and EvTSR design versus previous best LEMMA | EvTSR · TextZoom (ASTER) | average accuracy: 66.0% -> 67.9% | Improved |
| EvTSR instead of LEMMA | EvTSR · TextZoom Easy (CRNN) | accuracy: 67.1% -> 66.0% | Mixed |
Closest papers by meaning
- Joint Framework for Single Image Reconstruction and Super-Resolution With an Event Camera (TPAMI 2021 · similarity 0.89)
- E2SRI: Learning to Super-Resolve Intensity Images From Events (TPAMI 2021 · similarity 0.88)
- EvTexture: Event-driven Texture Enhancement for Video Super-Resolution (ICML 2024 · similarity 0.87)
- EvSTVSR: Event Guided Space-Time Video Super-Resolution (AAAI 2025 · similarity 0.86)
- Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · similarity 0.86)
- EventGPT: Event Stream Understanding with Multimodal Large Language Models (CVPR 2025 · similarity 0.85)
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.
