Research map / Image generation / Image restoration
Efficient and Explicit Modelling of Image Hierarchies for Image Restoration
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use GRL-B instead of Restormer | Single-image motion deblurring · GoPro | PSNR: 32.92 -> 33.93 | Helped |
| Use GRL-B instead of Restormer | Single-image motion deblurring · HIDE | PSNR: 31.22 -> 31.65 | Helped |
| Use GRL-B instead of Restormer | Color denoising · Urban100, σ=50 | PSNR: 30.02 -> 30.46 | Helped |
| Use dot product instead of Euclidean distance for similarity comparison (ablation) | Anchored stripe self-attention · Color denoising, BSD68, σ=15 | PSNR: 35.02 -> 35.10 | Helped |
| Use dot product instead of Euclidean distance for similarity comparison (ablation) | Anchored stripe self-attention · Image SR, BSD100, ×4 | PSNR: 27.67 -> 27.70 | Helped |
| Use average pooling followed by linear projection for anchors rather than patch merging (ablation) | Anchored stripe self-attention · Set5 | PSNR: 34.98 -> 35.03 | Helped |
| Use average pooling followed by linear projection for anchors rather than max pooling followed by linear projection (ablation) | Anchored stripe self-attention · Set5 | PSNR: 35.02 -> 35.03 | Helped |
| Replace average pooling plus linear projection with depthwise convolution for anchor projection (ablation) | Anchored stripe self-attention · Set5 | PSNR: 35.03 -> 35.03 | No clear effect |
| Replace average pooling plus linear projection with convolution for anchor projection (ablation) | Anchored stripe self-attention · Set5 | PSNR: 35.03 -> 35.03 | No clear effect |
Closest papers by meaning
- ACL: Activating Capability of Linear Attention for Image Restoration (CVPR 2025 · similarity 0.87)
- Omni-Kernel Network for Image Restoration (AAAI 2024 · similarity 0.85)
- Sharing Key Semantics in Transformer Makes Efficient Image Restoration (NeurIPS 2024 · similarity 0.85)
- Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration (CVPR 2024 · similarity 0.85)
- Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration (AAAI 2024 · similarity 0.84)
- Efficient Visual State Space Model for Image Deblurring (CVPR 2025 · similarity 0.84)
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.