mlsanityData to 7 Oct 2026

EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis

arXiv 1612.07919 ↗First posted 23 Dec 2016cs.CV cs.AI stat.MLcited by 177

Not on the map. Why?

Abstract (arXiv)

Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input. Traditionally, the performance of algorithms for this task is measured using pixel-wise reconstruction measures such as peak signal-to-noise ratio (PSNR) which have been shown to correlate poorly with the human perception of image quality. As a result, algorithms minimizing these metrics tend to produce over-smoothed images that lack high-frequency textures and do not look natural despite yielding high PSNR values. We propose a novel application of automated texture synthesis in combination with a perceptual loss focusing on creating realistic textures rather than optimizing for a pixel-accurate reproduction of ground truth images during training. By using feed-forward fully convolutional neural networks in an adversarial training setting, we achieve a significant boost in image quality at high magnification ratios. Extensive experiments on a number of datasets show the effectiveness of our approach, yielding state-of-the-art results in both quantitative and qualitative benchmarks.

Key facts. Cited by 177 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 58; 2022: 48; 2023: 25; 2024: 28; 2025: 11; 2026: 7.

177 papers.

Sort:

By area:

  1. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  2. 2021Transformers in Vision: A Surveycited by 1,009
  3. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  4. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  5. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  6. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  7. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  8. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 235
  9. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 222
  10. 2022MAT: Mask-Aware Transformer for Large Hole Image Inpaintingcited by 216
  11. 2021Projected GANs Converge Fastercited by 204
  12. 2022Generative Modelling With Inverse Heat Dissipationcited by 164
38 more
  1. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  2. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  3. 2022FILM: Frame Interpolation for Large Motioncited by 149
  4. 2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
  5. 2022Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolutioncited by 96
  6. 2021NeRF-SR: High-Quality Neural Radiance Fields using Supersamplingcited by 95
  7. 2021Blind Image Super-Resolution: A Survey and Beyondcited by 93
  8. 2022Accurate Image Restoration with Attention Retractable Transformercited by 85
  9. 2022Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registrationcited by 80
  10. 2021MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolutioncited by 79
  11. 2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
  12. 2021Robust Reference-based Super-Resolution via C2-Matchingcited by 68
  13. 2022SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolutioncited by 67
  14. 2021Burst Image Restoration and Enhancementcited by 64
  15. 2023EDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-Resolutioncited by 56
  16. 2021A Theory of the Distortion-Perception Tradeoff in Wasserstein Spacecited by 52
  17. 2022Reference-based Image Super-Resolution with Deformable Attention Transformercited by 50
  18. 2021WaveFill: A Wavelet-based Generation Network for Image Inpaintingcited by 44
  19. 2022Shift-tolerant Perceptual Similarity Metriccited by 44
  20. 2024NTIRE 2024 Challenge on Image Super-Resolution (x4): Methods and Resultscited by 40
  21. 2022MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpaintingcited by 35
  22. 2021Dual-Camera Super-Resolution with Aligned Attention Modulescited by 33
  23. 2022DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualizationcited by 32
  24. 2022BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignmentcited by 32
  25. 2021Best-Buddy GANs for Highly Detailed Image Super-Resolutioncited by 30
  26. 2024TexPainter: Generative Mesh Texturing with Multi-view Consistencycited by 29
  27. 2021GMLight: Lighting Estimation via Geometric Distribution Approximationcited by 28
  28. 2021COMISR: Compression-Informed Video Super-Resolutioncited by 26
  29. 2021Anchor-based Plain Net for Mobile Image Super-Resolutioncited by 24
  30. 2024Dynamic Conditional Optimal Transport through Simulation-Free Flowscited by 24
  31. 2021A Comprehensive Review of Deep Learning-based Single Image Super-resolutioncited by 23
  32. 2024DVMSR: Distillated Vision Mamba for Efficient Super-Resolutioncited by 23
  33. 2022A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Boundscited by 22
  34. 2022Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advancescited by 21
  35. 2022Perception-Oriented Single Image Super-Resolution using Optimal Objective Estimationcited by 21
  36. 2023Super-NeRF: View-consistent Detail Generation for NeRF super-resolutioncited by 21
  37. 2022AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Resultscited by 20
  38. 2023Human Guided Ground-truth Generation for Realistic Image Super-resolutioncited by 20

50 most cited of 177 All 177 (JSON)