Research map / Image generation / Super-resolution
Rotation Equivariant Arbitrary-Scale Image Super-Resolution
Qi Xie, Jiahong Fu, Zongben Xu, Deyu Meng
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 |
|---|---|---|---|
| make INR and encoder rotation equivariant | EDSR-LIIF · Urban100 x2 | PSNR (dB): 32.18 -> 32.39 | Improved |
| make INR and encoder rotation equivariant | EDSR-OPE · Urban100 x2 | PSNR (dB): 31.93 -> 32.00 | Improved |
| make INR and encoder rotation equivariant | EDSR-LTE · Urban100 x2 | PSNR (dB): 32.28 -> 32.43 | Improved |
| make INR and encoder rotation equivariant | RDN-LIIF · Urban100 x2 | PSNR (dB): 32.90 -> 33.06 | Improved |
| make INR and encoder rotation equivariant | RDN-OPE · Urban100 x2 | PSNR (dB): 32.65 -> 32.75 | Improved |
| make INR and encoder rotation equivariant | RDN-LTE · Urban100 x2 | PSNR (dB): 33.03 -> 33.23 | Improved |
| make INR and encoder rotation equivariant | SwinIR-LIIF · Urban100 x2 | PSNR (dB): 33.34 -> 33.54 | Improved |
| make INR and encoder rotation equivariant | SwinIR-OPE · Urban100 x2 | PSNR (dB): 33.12 -> 33.35 | Improved |
| make INR and encoder rotation equivariant | SwinIR-LTE · Urban100 x2 | PSNR (dB): 33.46 -> 33.67 | Improved |
| make INR and encoder rotation equivariant | SwinIR-LTE · parameter count | parameters: 13.7M -> 7.7M | Improved |
| make INR and encoder rotation equivariant | LIIF · DIV2K p4 equivariance error x4 (trained) | NMAE: 0.197 -> 1e-02 | Improved |
| make INR and encoder rotation equivariant | EDSR-LIIF · Set5 x8 (out-scale SR) | PSNR (dB): 26.98 -> 26.95 | Hurt |
Closest papers by meaning
- Deep Arbitrary-Scale Image Super-Resolution via Scale-Equivariance Pursuit (CVPR 2023 · similarity 0.90)
- A Regularization-Guided Equivariant Approach for Image Restoration (CVPR 2025 · similarity 0.86)
- Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors (AAAI 2025 · similarity 0.86)
- Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder (CVPR 2024 · similarity 0.86)
- Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction (NeurIPS 2026 · similarity 0.85)
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.85)
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.
