Research map / Image generation / Image restoration
Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration
Shihao Zhou, Jinshan Pan, Jinglei Shi, Duosheng Chen, Lishen Qu, Jufeng Yang
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 |
|---|---|---|---|
| replace multiple dynamic convolution with gated dynamic decoupler (GDD) (ablation) | FPro · SPAD | PSNR: 48.52 -> 48.91 | Improved |
| share a single GDD across the DPBs (ablation) | FPro · SPAD | PSNR: 48.91 -> 48.99 | Improved |
| add high-frequency prompt modulator (HPM) (ablation) | FPro · SPAD | PSNR: 48.77 -> 48.99 | Improved |
| add low-frequency prompt modulator (LPM) (ablation) | FPro · SPAD | PSNR: 48.89 -> 48.99 | Improved |
| frequency prompts instead of spatial prompts (FPro vs PromptIR) | prompt-based restoration · Rain100L | PSNR: 37.04 -> 39.20 | Improved |
| frequency prompts vs PromptRestorer (which used extra training data) | prompt-based restoration · Rain100L | PSNR: 39.04 -> 39.20 | Improved |
| FPro vs DRSformer | real rain removal · SPAD | PSNR: 48.53 -> 48.99 | Improved |
| FPro vs best SSIM baselines | FPro · SPAD SSIM / TIP-2018 SSIM | SSIM: 0.9936 vs 0.9941 (SCD-Former); 0.879 vs 0.894 (Wang et al.) | Mixed |
| FPro vs DRSformer on compute | FPro · SPAD efficiency | FLOPs/G: 242.9 -> 81.9 | Improved |
| FPro vs prior methods on NIQE | FPro · real rainy images | NIQE: 5.5942 -> 5.2999 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 2 of 2 shared results
- PromptIR — PromptIR: Prompting for All-in-One Image Restoration (NeurIPS 2023) · better on 1 of 1 shared result
- PromptRestorer — PromptRestorer: A Prompting Image Restoration Method with Degradation Perception (NeurIPS 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification (AAAI 2025 · similarity 0.86)
- Dual Prompting Image Restoration with Diffusion Transformers (CVPR 2025 · similarity 0.86)
- SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency (AAAI 2024 · similarity 0.85)
- Improving the Learning Capability of Small-size Image Restoration Network by Deep Fourier Shifting (NeurIPS 2024 · similarity 0.85)
- Efficient RAW Image Deblurring with Adaptive Frequency Modulation (NeurIPS 2025 · similarity 0.85)
- Intra and Inter Parser-Prompted Transformers for Effective Image Restoration (AAAI 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.
