Research map / Image generation / Super-resolution
SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation
Sanghyun Son, Kyoung Mu Lee
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 |
|---|---|---|---|
| Use SRWarp instead of ×4 SR followed by bicubic warping | image warping · DIV2KW Test | mPSNR (dB): 30.76 -> 31.04 | Improved |
| Use SRWarp for arbitrary-scale SR | B100 · scale ×2.0 to ×4.0 | PSNR (dB): 32.33 vs. 32.31; 31.45 -> 31.46; 30.46 -> 30.46; 29.69 -> 29.71; 29.26 -> 29.27; 28.88 -> 28.89; 28.41 -> 28.42; 28.01 - | Mixed |
| Add adaptive warping, multiscale blending, and reconstruction (ablation) | MDSR baseline · DIV2KW Valid. | mPSNR (dB): 31.36 -> 32.29 | Improved |
| Add multiscale blending (ablation) | MDSR with AWL and reconstruction · DIV2KW Valid. | mPSNR (dB): 32.19 -> 32.29 | Improved |
| Add reconstruction module (ablation) | MDSR with AWL and multiscale blending · DIV2KW Valid. | mPSNR (dB): 32.21 -> 32.29 | Improved |
| Add adaptive warping layer (ablation) | MDSR with multiscale blending and reconstruction · DIV2KW Valid. | mPSNR (dB): 32.19 -> 32.29 | Improved |
| Use adaptive coordinates with fixed cubic-spline weights (ablation) | SRWarp warping layer · DIV2KW Valid. | mPSNR (dB): 32.19 | No clear effect |
| Use learned kernels on a regular grid (ablation) | SRWarp warping layer · DIV2KW Valid. | mPSNR (dB): 32.19 -> 32.25 | Improved |
| Combine adaptive coordinates with a learned kernel estimator (ablation) | SRWarp warping layer · DIV2KW Valid. | mPSNR (dB): 32.25 -> 32.29 | Improved |
| Use scale-specific kernel estimators (ablation) | AWL · DIV2KW Valid. | mPSNR (dB): +0.01dB | Improved |
| Estimate resampling kernels depthwise (ablation) | AWL · DIV2KW Valid. | mPSNR (dB): +0.05dB | Improved |
| Average warped features across scales instead of using the proposed blending (ablation) | SRWarp multiscale blending · DIV2KW Valid. | mPSNR (dB): 32.26 -> 32.29 | Hurt |
Closest papers by meaning
- Deep Learning for Image Super-Resolution: A Survey (TPAMI 2020 · similarity 0.90)
- Recursive Generalization Transformer for Image Super-Resolution (ICLR 2024 · similarity 0.88)
- GSDD: Generative Space Dataset Distillation for Image Super-resolution (AAAI 2024 · similarity 0.87)
- Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary (CVPR 2024 · similarity 0.87)
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 2024 · similarity 0.87)
- Image Processing GNN: Breaking Rigidity in Super-Resolution (CVPR 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.
