Research map / Image generation / Super-resolution
Deep Arbitrary-Scale Image Super-Resolution via Scale-Equivariance Pursuit
Read the paperCheck 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 |
|---|---|---|---|
| Add AFE to the EQSR backbone (ablation) | EQSR · Urban100 ×6 | PSNR: 24.52 -> 24.66 | Helped |
| Add Neural Kriging as the full upsampler (ablation) | EQSR baseline · Urban100 ×6 | PSNR: 24.23 -> 24.63 | Helped |
| Use only data kernels in the upsampler (ablation) | EQSR baseline · Urban100 ×2 | PSNR: 33.17 -> 33.34 | Helped |
| Use only scale kernels in the upsampler (ablation) | EQSR baseline · Urban100 ×2 | PSNR: 33.17 -> 32.26 | Hurt |
| Add Scale-Aware Convolution (ablation) | Model C · Urban100 ×2 | PSNR: 33.54 -> 33.59 | Helped |
| Pre-train the model on ImageNet | EQSR · Urban100 ×2 | PSNR: 33.62 -> 33.83 | Helped |
| Use EQSR rather than LTE | ASISR · Urban100 ×3 | PSNR: 29.41 -> 29.76 | Helped |
| Use EQSR rather than LTE | ASISR · Urban100 ×6 (out-of-distribution) | PSNR: 24.62 -> 24.83 | Helped |
| Use EQSR rather than LTE | ASISR · Set5 ×6 (out-of-distribution) | PSNR: 29.50 -> 29.51 | No clear effect |
Closest papers by meaning
- SAVSR: Arbitrary-Scale Video Super-Resolution via a Learned Scale-Adaptive Network (AAAI 2024 · similarity 0.89)
- Arbitrary-Scale Image Generation and Upsampling using Latent Diffusion Model and Implicit Neural Decoder (CVPR 2024 · similarity 0.88)
- Hierarchical Neural Operator Transformer with Learnable Frequency-aware Loss Prior for Arbitrary-scale Super-resolution (ICML 2024 · similarity 0.86)
- Arbitrary-Scale Video Super-resolution Guided by Dynamic Context (AAAI 2024 · similarity 0.86)
- GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution (AAAI 2025 · similarity 0.86)
- Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World (CVPR 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.