Research map / Image generation / Super-resolution
Spatially-Variant Degradation Model for Dataset-free Super-resolution
SHAOJIE GUO, Haofei Song, Qingli Li, Yan Wang
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 |
|---|---|---|---|
| use spatially-variant degradation (5 atom kernels) instead of a single spatially-invariant kernel (ablation) | SVDSR · Manga109 x2 | PSNR: 29.23 -> 29.89 | Improved |
| increase number of atom kernels beyond 5 (ablation) | SVDSR · Set5 x2 | PSNR: 33.51 -> 33.43 -> 33.27 (N_D 5 -> 7 -> 9) | Hurt |
| add instance normalization layer to the generator (ablation) | SVDSR · Set14 x2 | PSNR: 29.28 -> 29.61 | Improved |
| add FFT-based frequency-domain skip connection (ablation) | SVDSR · Set14 x2 | PSNR: 29.52 -> 29.61 | Improved |
| add frequency-domain likelihood term (ablation) | SVDSR · Set14 x2 | PSNR: 29.61 -> 29.61 | No clear effect |
| spatially-variant model versus BSRDM at scale x4 | SVDSR · Set14 x4 | PSNR: 26.63 -> 26.81 | Improved |
| spatially-variant model versus BSRDM at scale x2 | SVDSR · Urban100 x2 | PSNR: 25.46 -> 26.40 | Improved |
| supply ground-truth kernel (non-blind) instead of estimating it (ablation) | SVDSR · Set5 x2 | PSNR: 33.51 -> 34.44 | Improved |
| per-pixel kernel estimation versus BSRDM | SVDSR · Set5 x2, 256x256 | runtime: 30s -> 33s | No clear effect |
Closest papers by meaning
- Blind Image Super-Resolution With Elaborate Degradation Modeling on Noise and Kernel (CVPR 2022 · similarity 0.90)
- Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV 2021 · similarity 0.88)
- LightBSR: Towards Lightweight Blind Super-Resolution via Discriminative Implicit Degradation Representation Learning (ICCV 2025 · similarity 0.87)
- Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution (AAAI 2025 · similarity 0.86)
- Unsupervised Diffusion-Based Degradation Modeling for Real-World Super-Resolution (AAAI 2025 · similarity 0.86)
- A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution (CVPR 2024 · 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.
