Research map / Image generation / Super-resolution
Towards Real Scene Super-Resolution With Raw Images
Xiangyu Xu, Yongrui Ma, Wenxiu Sun
Check 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 the color correction branch (ablation) | Ours full model · Synthetic dataset, Blind | PSNR: 20.54 -> 30.79 | Improved |
| add the color correction branch (ablation) | Ours full model · Synthetic dataset, Non-blind | PSNR: 21.13 -> 31.79 | Improved |
| use pixel-wise rather than global color correction (ablation) | Ours full model · Synthetic dataset, Blind | SSIM: 0.7954 -> 0.8044 | Improved |
| use pixel-wise rather than global color correction (ablation) | Ours full model · Synthetic dataset, Non-blind | SSIM: 0.8095 -> 0.8272 | Improved |
| use raw input alongside the low-resolution color image (ablation) | Ours full model · Synthetic dataset, Blind | SSIM: 0.7827 -> 0.8044 | Improved |
| use raw input alongside the low-resolution color image (ablation) | Ours full model · Synthetic dataset, Non-blind | SSIM: 0.7921 -> 0.8272 | Improved |
| add feature fusion from the restoration branch to color correction (ablation) | Ours full model · Synthetic dataset, Blind | PSNR: 30.73 -> 30.79 | Improved |
| add feature fusion from the restoration branch to color correction (ablation) | Ours full model · Synthetic dataset, Non-blind | PSNR: 31.68 -> 31.79 | Improved |
| train RDN with data generated by the camera-imaging simulation pipeline | RDN · Real captured images | visual sharpness | Improved |
Closest papers by meaning
- Exploiting Raw Images for Real-Scene Super-Resolution (TPAMI 2020 · similarity 0.95)
- Learning To Zoom Inside Camera Imaging Pipeline (CVPR 2022 · similarity 0.91)
- Image Super-Resolution Using Deep Convolutional Networks (TPAMI 2016 · similarity 0.90)
- Natural and Realistic Single Image Super-Resolution With Explicit Natural Manifold Discrimination (CVPR 2019 · similarity 0.90)
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (CVPR 2016 · similarity 0.89)
- Towards Realistic Data Generation for Real-World Super-Resolution (ICLR 2025 · similarity 0.89)
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.
