mlsanityData to 7 Oct 2026

StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces

arXiv 2303.06146 ↗First posted 10 Mar 2023cs.CV cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

Recent advances in face manipulation using StyleGAN have produced impressive results. However, StyleGAN is inherently limited to cropped aligned faces at a fixed image resolution it is pre-trained on. In this paper, we propose a simple and effective solution to this limitation by using dilated convolutions to rescale the receptive fields of shallow layers in StyleGAN, without altering any model parameters. This allows fixed-size small features at shallow layers to be extended into larger ones that can accommodate variable resolutions, making them more robust in characterizing unaligned faces. To enable real face inversion and manipulation, we introduce a corresponding encoder that provides the first-layer feature of the extended StyleGAN in addition to the latent style code. We validate the effectiveness of our method using unaligned face inputs of various resolutions in a diverse set of face manipulation tasks, including facial attribute editing, super-resolution, sketch/mask-to-face translation, and face toonification.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 38 of its 46 references that are in the map. First posted on arXiv 10 Mar 2023.

Builds on

38 of 46 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
  5. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  6. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  7. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  8. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  9. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  10. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  11. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  12. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
26 more
  1. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  2. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  3. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  4. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  5. 2021Pivotal Tuning for Latent-based Editing of Real Imagescited by 427
  6. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  7. 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
  8. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  9. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 348
  10. 2021ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinementcited by 248
  11. 2021High-Fidelity GAN Inversion for Image Attribute Editingcited by 197
  12. 2022StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGANcited by 169
  13. 2020GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolutioncited by 158
  14. 2021Talk-to-Edit: Fine-Grained Facial Editing via Dialogcited by 102
  15. 2020Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domainscited by 96
  16. 2021HyperInverter: Improving StyleGAN Inversion via Hypernetworkcited by 85
  17. 2020StyleGAN2 Distillation for Feed-forward Image Manipulationcited by 78
  18. 2022Stitch it in Time: GAN-Based Facial Editing of Real Videoscited by 68
  19. 2020TSIT: A Simple and Versatile Framework for Image-to-Image Translationcited by 64
  20. 2021GAN Inversion for Out-of-Range Images with Geometric Transformationscited by 55
  21. 2022Third Time's the Charm? Image and Video Editing with StyleGAN3cited by 54
  22. 2021Low-Rank Subspaces in GANscited by 52
  23. 2021StyleAlign: Analysis and Applications of Aligned StyleGAN Modelscited by 48
  24. 2020PIE: Portrait Image Embedding for Semantic Controlcited by 41
  25. 2022Spatially-Adaptive Multilayer Selection for GAN Inversion and Editingcited by 39
  26. 2022VToonify: Controllable High-Resolution Portrait Video Style Transfercited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 6; 2025: 8; 2026: 1.

19 papers.

Sort:

By area:

  1. 2025Controllable Video Generation: A Surveycited by 93
  2. 2023RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatarscited by 45
  3. 2024TextToon: Real-Time Text Toonify Head Avatar from Single Videocited by 21
  4. 2025Generative AI for Cel-Animation: A Surveycited by 17
  5. 2024Deformable One-shot Face Stylization via DINO Semantic Guidancecited by 14
  6. 2023RIGID: Recurrent GAN Inversion and Editing of Real Face Videoscited by 13
  7. 2024BeautyBank: Encoding Facial Makeup in Latent Spacecited by 4
  8. 2025Collaboration and Controversy Among Experts: Rumor Early Detection by Tuning a Comment Generatorcited by 4
  9. 2025TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detectioncited by 4
  10. 2023Video Face Re-Aging: Toward Temporally Consistent Face Re-Agingcited by 3
  11. 2024ToonAging: Face Re-Aging upon Artistic Portrait Style Transfercited by 2
  12. 2025ToonifyGB: StyleGAN-based Gaussian Blendshapes for 3D Stylized Head Avatarscited by 2
7 more
  1. 2024S3Editor: A Sparse Semantic-Disentangled Self-Training Framework for Face Video Editingcited by 1
  2. 2023Subjective Face Transform using Human First Impressionscited by 0
  3. 2024Real Face Video Animation Platformcited by 0
  4. 2025Geometry-Aware Texture Generation for 3D Head Modeling with Artist-driven Controlcited by 0
  5. 2025GaitCrafter: Diffusion Model for Biometric Preserving Gait Synthesiscited by 0
  6. 2025DeepForgeSeal: Latent Space-Driven Semi-Fragile Watermarking for Deepfake Detection Using Adversarial Reinforcement Learningcited by 0
  7. 2026ReAge3D: Re-Aging 3D Faces with View Consistencycited by 0