Research map / Image generation / Super-resolution
Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform
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 |
|---|---|---|---|
| Condition SR features on segmentation probability maps using SFT layers | SFT-GAN · OutdoorSceneTest | texture realism | Helped |
| Use SFT-GAN instead of SRGAN | OutdoorSceneTest · OutdoorSceneTest | texture naturalness | Helped |
| Use SFT-GAN instead of EnhanceNet | OutdoorSceneTest · OutdoorSceneTest | texture naturalness | Helped |
| Use SFT-GAN instead of MemNet | OutdoorSceneTest · OutdoorSceneTest | visual quality | Helped |
| Replace spatial feature modulation with segmentation-map concatenation at the input (ablation) | SFT-GAN · OutdoorSceneTest | perceptual quality | Hurt |
| Replace SFT with compositional class-specific mapping (ablation) | SFT-GAN · OutdoorSceneTest | parameter count: ×2.5 parameters as ours | Hurt |
| Replace spatial-wise modulation with FiLM's spatially uniform feature modulation (ablation) | SFT-GAN · OutdoorSceneTest | perceptual quality | Hurt |
| Provide no usable segmentation prior, so regions use the background/default modulation (ablation) | SFT-GAN · Out-of-category examples | visual quality | No clear effect |
Closest papers by meaning
- Learning Texture Transformer Network for Image Super-Resolution (CVPR 2020 · similarity 0.91)
- Natural and Realistic Single Image Super-Resolution With Explicit Natural Manifold Discrimination (CVPR 2019 · similarity 0.90)
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (CVPR 2017 · similarity 0.90)
- SeD: Semantic-Aware Discriminator for Image Super-Resolution (CVPR 2024 · similarity 0.88)
- Exploring Semantic Feature Discrimination for Perceptual Image Super-Resolution and Opinion-Unaware No-Reference Image Quality Assessment (CVPR 2025 · similarity 0.86)
- Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary (CVPR 2024 · similarity 0.86)
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.