Research map / Image generation / Image restoration
Improving Image Restoration by Revisiting Global Information Aggregation
Xiaojie Chu, Liangyu Chen, Chengpeng Chen, Xin Lu
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 TLC at inference | HINet · GoPro (single-image deblurring) | PSNR: 32.71 -> 33.08 | Improved |
| add TLC at inference | MPRNet · GoPro (single-image deblurring) | PSNR: 32.66 -> 33.31 | Improved |
| add TLC at inference | Restormer · GoPro (single-image deblurring) | PSNR: 32.92 -> 33.57 | Improved |
| add TLC at inference | Restormer · HIDE (single-image deblurring) | PSNR: 31.22 -> 31.49 | Improved |
| add TLC at inference | RNN-MBP · GoPro (video deblurring) | PSNR: 33.32 -> 33.80 | Improved |
| add TLC at inference | Restormer · DPDD dual-pixel defocus (combined) | PSNR: 26.66 -> 27.02 | Improved |
| add TLC at inference | Restormer · Urban100 color denoising sigma=50 (single model) | PSNR: 30.02 -> 30.16 | Improved |
| add TLC at inference | SPDNet · SPA-Data deraining | PSNR: 43.55 -> 43.73 | Improved |
| add TLC at inference | FFANet · SOTS outdoor dehazing | PSNR: 33.57 -> 33.99 | Improved |
| add TLC to Instance Normalization (ablation) | UNet · GoPro (UNet with module) | PSNR: 30.95 -> 31.11 | Improved |
| add TLC to Squeeze-and-Excitation (ablation) | UNet · GoPro (UNet with module) | PSNR: 30.82 -> 31.21 | Improved |
| add TLC to CBAM (ablation) | UNet · GoPro (UNet with module) | PSNR: 30.53 -> 31.05 | 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 7 of 7 shared results
- HINet — HiNet: Deep Image Hiding by Invertible Network (ICCV 2021) · better on 2 of 2 shared results
- FFANet — FFA-Net: Feature Fusion Attention Network for Single Image Dehazing (AAAI 2020) · 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
- Learning Where and What to Restore for Composite Image Restoration (NeurIPS 2026 · similarity 0.87)
- Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration (NeurIPS 2026 · similarity 0.87)
- Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts (NeurIPS 2024 · similarity 0.86)
- Test-Time Degradation Adaptation for Open-Set Image Restoration (ICML 2024 · similarity 0.86)
- Debiased All-in-one Image Restoration with Task Uncertainty Regularization (AAAI 2025 · similarity 0.86)
- MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration (CVPR 2025 · 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.
