mlsanityData to 7 Oct 2026

Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis

arXiv 1601.04589 ↗First posted 18 Jan 2016cs.CVcited by 102

Not on the map. Why?

Abstract (arXiv)

This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D images. The generative MRF acts on higher-levels of a dCNN feature pyramid, controling the image layout at an abstract level. We apply the method to both photographic and non-photo-realistic (artwork) synthesis tasks. The MRF regularizer prevents over-excitation artifacts and reduces implausible feature mixtures common to previous dCNN inversion approaches, permitting synthezing photographic content with increased visual plausibility. Unlike standard MRF-based texture synthesis, the combined system can both match and adapt local features with considerable variability, yielding results far out of reach of classic generative MRF methods.

Key facts. Cited by 102 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Jan 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 30; 2023: 24; 2024: 12; 2025: 5; 2026: 6.

102 papers.

Sort:

By area:

  1. 2021More Control for Free! Image Synthesis with Semantic Diffusion Guidancecited by 211
  2. 2022Splicing ViT Features for Semantic Appearance Transfercited by 209
  3. 2022ARF: Artistic Radiance Fieldscited by 147
  4. 2021ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flowscited by 113
  5. 2022Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfercited by 66
  6. 2021StyleMesh: Style Transfer for Indoor 3D Scene Reconstructionscited by 58
  7. 2021Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfercited by 41
  8. 2023Neural Preset for Color Style Transfercited by 36
  9. 2021Feature-based Style Randomization for Domain Generalizationcited by 34
  10. 2022NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fieldscited by 33
  11. 2023DiffFashion: Reference-based Fashion Design with Structure-aware Transfer by Diffusion Modelscited by 33
  12. 2025Attention Distillation: A Unified Approach to Visual Characteristics Transfercited by 32
38 more
  1. 2022Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Trainingcited by 29
  2. 2022Learning Graph Neural Networks for Image Style Transfercited by 29
  3. 2021In the light of feature distributions: moment matching for Neural Style Transfercited by 26
  4. 2022Generating natural images with direct Patch Distributions Matchingcited by 26
  5. 2022RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmarkcited by 24
  6. 2022Semantic Segmentation in Art Paintingscited by 23
  7. 2022Neural Neighbor Style Transfercited by 23
  8. 2021Exemplar-Based 3D Portrait Stylizationcited by 21
  9. 2022AesUST: Towards Aesthetic-Enhanced Universal Style Transfercited by 21
  10. 2021SOUP-GAN: Super-Resolution MRI Using Generative Adversarial Networkscited by 18
  11. 2022Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filterscited by 17
  12. 2021Training a Task-Specific Image Reconstruction Losscited by 16
  13. 2022All-to-key Attention for Arbitrary Style Transfercited by 16
  14. 2024Geometry Transfer for Stylizing Radiance Fieldscited by 16
  15. 2022Spatial Mixture-of-Expertscited by 14
  16. 2024CoARF: Controllable 3D Artistic Style Transfer for Radiance Fieldscited by 14
  17. 2021Texture Reformer: Towards Fast and Universal Interactive Texture Transfercited by 12
  18. 2024Reference-based Controllable Scene Stylization with Gaussian Splattingcited by 12
  19. 2021DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfercited by 11
  20. 2022Neural Graphical Modelscited by 11
  21. 2025Video Color Grading via Look-Up Table Generationcited by 9
  22. 2021dualFace:Two-Stage Drawing Guidance for Freehand Portrait Sketchingcited by 8
  23. 2021Deep Translation Prior: Test-time Training for Photorealistic Style Transfercited by 8
  24. 2022Controllable Style Transfer via Test-time Training of Implicit Neural Representationcited by 8
  25. 2023Advances in 3D Neural Stylization: A Surveycited by 8
  26. 2021Rethinking Content and Style: Exploring Bias for Unsupervised Disentanglementcited by 7
  27. 2021Meta Internal Learningcited by 7
  28. 2024Creativity in AI: Progresses and Challengescited by 7
  29. 2025ABC-GS: Alignment-Based Controllable Style Transfer for 3D Gaussian Splattingcited by 7
  30. 2021DRAN: Detailed Region-Adaptive Normalization for Conditional Image Synthesiscited by 6
  31. 2021How Deep Are the Fakes? Focusing on Audio Deepfake: A Surveycited by 6
  32. 2021A-ESRGAN: Training Real-World Blind Super-Resolution with Attention U-Net Discriminatorscited by 6
  33. 2023Instruct-Video2Avatar: Video-to-Avatar Generation with Instructionscited by 6
  34. 2022Quality Metric Guided Portrait Line Drawing Generation from Unpaired Training Datacited by 5
  35. 2022Learning to Incorporate Texture Saliency Adaptive Attention to Image Cartoonizationcited by 5
  36. 2022Vision-Language Matching for Text-to-Image Synthesis via Generative Adversarial Networkscited by 5
  37. 2023Disentangling Structure and Appearance in ViT Feature Spacecited by 5
  38. 2024G-Style: Stylized Gaussian Splattingcited by 5

50 most cited of 102 All 102 (JSON)