Research map / Image generation / Super-resolution
Deep Constrained Least Squares for Blind Image Super-Resolution
Check 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 DCLS instead of DANv2 | blind super-resolution · DIV2KRK ×4 | PSNR: 28.74 -> 28.99 | Helped |
| use DCLS instead of DANv2 | blind super-resolution · DIV2KRK ×2 | PSNR: 32.58 -> 32.75 | Helped |
| add DCLS deconvolution (ablation) | DCLS with DDLK and DPAN · DIV2KRK ×4 | PSNR: 28.86 -> 28.99 | Helped |
| add DPAN (ablation) | DCLS with DDLK and DCLS deconvolution · DIV2KRK ×4 | PSNR: 28.94 -> 28.99 | Helped |
| replace SLK with DDLK (ablation) | DCLS with stretching and DPAN, without DCLS deconvolution · DIV2KRK ×4 | PSNR: 28.84 -> 28.86 | Helped |
| replace SLK with DDLK (ablation) | DCLS with DCLS deconvolution and DPAN, without stretching · DIV2KRK ×4 | PSNR: 28.94 -> 28.99 | Helped |
| use DCLS rather than Wiener deconvolution (ablation) | feature-space deconvolution · Set5 | PSNR: 32.05 -> 32.12 | Helped |
| use DCLS rather than CLS deconvolution (ablation) | feature-space deconvolution · Set5 | PSNR: 31.98 -> 32.12 | Helped |
| apply deconvolution in feature space rather than RGB space (ablation) | DCLS reconstruction · DIV2KRK ×4 | SSIM: 0.7941 -> 0.7964 | Helped |
Closest papers by meaning
- Blind Super-Resolution With Iterative Kernel Correction (CVPR 2019 · similarity 0.92)
- Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution (NeurIPS 2021 · similarity 0.91)
- A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution (CVPR 2024 · similarity 0.91)
- Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution (AAAI 2025 · similarity 0.89)
- Navigating Beyond Dropout: An Intriguing Solution towards Generalizable Image Super Resolution (CVPR 2024 · similarity 0.87)
- Noise-Free Optimization in Early Training Steps for Image Super-resolution (AAAI 2024 · similarity 0.87)
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.