mlsanityData to 7 Oct 2026

Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform

arXiv 1804.02815 ↗First posted 9 Apr 2018cs.CVcited by 369

Not on the map. Why?

Cited by 67 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Despite that convolutional neural networks (CNN) have recently demonstrated high-quality reconstruction for single-image super-resolution (SR), recovering natural and realistic texture remains a challenging problem. In this paper, we show that it is possible to recover textures faithful to semantic classes. In particular, we only need to modulate features of a few intermediate layers in a single network conditioned on semantic segmentation probability maps. This is made possible through a novel Spatial Feature Transform (SFT) layer that generates affine transformation parameters for spatial-wise feature modulation. SFT layers can be trained end-to-end together with the SR network using the same loss function. During testing, it accepts an input image of arbitrary size and generates a high-resolution image with just a single forward pass conditioned on the categorical priors. Our final results show that an SR network equipped with SFT can generate more realistic and visually pleasing textures in comparison to state-of-the-art SRGAN and EnhanceNet.

Key facts. Cited by 369 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 61; 2022: 71; 2023: 68; 2024: 79; 2025: 57; 2026: 33.

369 papers.

Sort:

By area:

  1. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  2. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  3. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  4. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  5. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  6. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 255
  7. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 253
  8. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  9. 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 230
  10. 2022StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANcited by 169
  11. 2021Low-Light Image and Video Enhancement Using Deep Learning: A Surveycited by 148
  12. 2023Efficient and Explicit Modelling of Image Hierarchies for Image Restorationcited by 145
38 more
  1. 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 133
  2. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 131
  3. 2022Deep Generalized Unfolding Networks for Image Restorationcited by 119
  4. 2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
  5. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  6. 2022Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priorscited by 98
  7. 2022Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolutioncited by 96
  8. 2021Blind Image Super-Resolution: A Survey and Beyondcited by 93
  9. 2024VmambaIR: Visual State Space Model for Image Restorationcited by 90
  10. 2023Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancementcited by 86
  11. 2021Iterative Filter Adaptive Network for Single Image Defocus Deblurringcited by 85
  12. 2022RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairscited by 85
  13. 2024Arbitrary-steps Image Super-resolution via Diffusion Inversioncited by 85
  14. 2021ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristiccited by 81
  15. 2021Towards Flexible Blind JPEG Artifacts Removalcited by 76
  16. 2022Multiscale Structure Guided Diffusion for Image Deblurringcited by 76
  17. 2023Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bankcited by 68
  18. 2023CoSeR: Bridging Image and Language for Cognitive Super-Resolutioncited by 66
  19. 2023HAT: Hybrid Attention Transformer for Image Restorationcited by 64
  20. 2024Degradation-Guided One-Step Image Super-Resolution with Diffusion Priorscited by 64
  21. 2021HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantizationcited by 58
  22. 2023Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancementcited by 57
  23. 2021Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transformcited by 56
  24. 2024Towards Extreme Image Compression with Latent Feature Guidance and Diffusion Priorcited by 56
  25. 2023ResDiff: Combining CNN and Diffusion Model for Image Super-Resolutioncited by 53
  26. 2021Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolutioncited by 52
  27. 2022CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Trainingcited by 49
  28. 2021AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsamplingcited by 47
  29. 2022Deep Constrained Least Squares for Blind Image Super-Resolutioncited by 47
  30. 2022NTIRE 2022 Challenge on Perceptual Image Quality Assessmentcited by 41
  31. 2023DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Modelscited by 41
  32. 2024XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolutioncited by 41
  33. 2022Learning Dual Memory Dictionaries for Blind Face Restorationcited by 40
  34. 2022GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priorscited by 39
  35. 2025UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Priorcited by 39
  36. 2021Text Prior Guided Scene Text Image Super-resolutioncited by 37
  37. 2021NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Resultscited by 36
  38. 2022NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Ratescited by 36

50 most cited of 369 All 369 (JSON)