mlsanityData to 7 Oct 2026

Stylized Face Sketch Extraction via Generative Prior with Limited Data

arXiv 2403.11263 ↗First posted 17 Mar 2024cs.CV cs.GRcited by 4

Not on the map. Why?

Abstract (arXiv)

Facial sketches are both a concise way of showing the identity of a person and a means to express artistic intention. While a few techniques have recently emerged that allow sketches to be extracted in different styles, they typically rely on a large amount of data that is difficult to obtain. Here, we propose StyleSketch, a method for extracting high-resolution stylized sketches from a face image. Using the rich semantics of the deep features from a pretrained StyleGAN, we are able to train a sketch generator with 16 pairs of face and the corresponding sketch images. The sketch generator utilizes part-based losses with two-stage learning for fast convergence during training for high-quality sketch extraction. Through a set of comparisons, we show that StyleSketch outperforms existing state-of-the-art sketch extraction methods and few-shot image adaptation methods for the task of extracting high-resolution abstract face sketches. We further demonstrate the versatility of StyleSketch by extending its use to other domains and explore the possibility of semantic editing. The project page can be found in https://kwanyun.github.io/stylesketch_project.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 62 of its 86 references that are in the map. First posted on arXiv 17 Mar 2024.

Builds on

62 of 86 references.

References · 62

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  7. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  8. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  10. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  11. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  12. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
38 more
  1. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  2. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  3. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  4. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  5. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  6. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  7. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 640
  8. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  9. 2015Holistically-Nested Edge Detectioncited by 590
  10. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  11. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  12. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  13. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 348
  14. 2020A Brief Review of Domain Adaptationcited by 287
  15. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 280
  16. 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
  17. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 206
  18. 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
  19. 2023StyleDrop: Text-to-Image Generation in Any Stylecited by 197
  20. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  21. 2021A Good Image Generator Is What You Need for High-Resolution Video Synthesiscited by 162
  22. 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
  23. 2020Few-shot Image Generation with Elastic Weight Consolidationcited by 122
  24. 2019MineGAN: effective knowledge transfer from GANs to target domains with few imagescited by 106
  25. 2019Image Generation From Small Datasets via Batch Statistics Adaptationcited by 102
  26. 2022BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotationscited by 99
  27. 2022Learning to generate line drawings that convey geometry and semanticscited by 82
  28. 2020StyleGAN2 Distillation for Feed-forward Image Manipulationcited by 78
  29. 2021Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networkscited by 68
  30. 2022Stitch it in Time: GAN-Based Facial Editing of Real Videoscited by 68
  31. 2019Photo-Sketching: Inferring Contour Drawings from Imagescited by 67
  32. 2021A Latent Transformer for Disentangled Face Editing in Images and Videoscited by 67
  33. 2022Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfercited by 66
  34. 2021GAN-Supervised Dense Visual Alignmentcited by 61
  35. 2022CLIPasso: Semantically-Aware Object Sketchingcited by 57
  36. 2021Anycost GANs for Interactive Image Synthesis and Editingcited by 54
  37. 2022Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignmentcited by 54
  38. 2020Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondencecited by 53

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2024Cross-Modal Few-Shot Learning: a Generative Transfer Learning Frameworkcited by 2
  2. 2025StrokeFusion: Vector Sketch Generation via Joint Stroke-UDF Encoding and Latent Sequence Diffusioncited by 2
  3. 2025FFaceNeRF: Few-shot Face Editing in Neural Radiance Fieldscited by 1
  4. 2025StyleMM: Stylized 3D Morphable Face Model via Text-Driven Aligned Image Translationcited by 1