Research map / Image generation / Super-resolution
D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution
Youwei Li, Haibin Huang, Lanpeng Jia, Haoqiang Fan, Shuaicheng Liu
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 divergence loss (triplet term) to the divergence network (ablation) | D2C-SR · RealSR x4 | PSNR: 29.43 -> 29.72 | Improved |
| add divergence loss (triplet term) to the divergence network (ablation) | D2C-SR · RealSR x2 | PSNR: 33.98 -> 34.40 | Improved |
| add divergence loss (triplet term) to the divergence network (ablation) | D2C-SR · RealSR x3 | PSNR: 31.12 -> 31.33 | Improved |
| add multi-branch deep residual structure (ablation) | D2C-SR · RealSR x4 | PSNR: 29.68 -> 29.72 | Improved |
| add multi-branch deep residual structure (ablation) | D2C-SR · RealSR x2 | PSNR: 34.28 -> 34.40 | Improved |
| increase tree width C from 1 to 4 (ablation) | D2C-SR small baseline · RealSR x4 | PSNR: 29.41 -> 29.58 | Improved |
| increase tree depth L from 1 to 4 (ablation) | D2C-SR small baseline · RealSR x4 | PSNR: 29.30 -> 29.64 | Improved |
| apply D2C structure to EDSR with fewer parameters | EDSR · RealSR x4 | PSNR: 29.09 -> 29.41 | Improved |
| apply D2C structure to VDSR | VDSR · RealSR x4 | PSNR: 27.07 -> 28.21 | Improved |
| apply D2C structure to SRResNet | SRResNet · RealSR x4 | SSIM: 0.825 -> 0.822 | Hurt |
| apply D2C structure to RDN | RDN · RealSR x4 | PSNR: 29.23 -> 29.32 | Improved |
| apply D2C structure to RRDBNet | RRDBNet · RealSR x4 | PSNR: 28.34 -> 28.47 | Improved |
Closest papers by meaning
- FSR: A General Frequency-Oriented Framework to Accelerate Image Super-resolution Networks (AAAI 2023 · similarity 0.90)
- Efficient Real-World Image Super-Resolution Via Adaptive Directional Gradient Convolution (IJCV 2026 · similarity 0.90)
- Component Divide-and-Conquer for Real-World Image Super-Resolution (ECCV 2020 · similarity 0.89)
- Towards Lightweight Super-Resolution With Dual Regression Learning (TPAMI 2024 · similarity 0.89)
- Accelerating the Super-Resolution Convolutional Neural Network (ECCV 2016 · similarity 0.89)
- GSDD: Generative Space Dataset Distillation for Image Super-resolution (AAAI 2024 · similarity 0.88)
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.
