mlsanityData to 14 Oct 2026

HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending

arXiv 2310.10651 ↗First posted 16 Oct 2023cs.CV cs.GRcited by 17

Not on the map. Why?

Abstract (arXiv)

Hair editing has made tremendous progress in recent years. Early hair editing methods use well-drawn sketches or masks to specify the editing conditions. Even though they can enable very fine-grained local control, such interaction modes are inefficient for the editing conditions that can be easily specified by language descriptions or reference images. Thanks to the recent breakthrough of cross-modal models (e.g., CLIP), HairCLIP is the first work that enables hair editing based on text descriptions or reference images. However, such text-driven and reference-driven interaction modes make HairCLIP unable to support fine-grained controls specified by sketch or mask. In this paper, we propose HairCLIPv2, aiming to support all the aforementioned interactions with one unified framework. Simultaneously, it improves upon HairCLIP with better irrelevant attributes (e.g., identity, background) preservation and unseen text descriptions support. The key idea is to convert all the hair editing tasks into hair transfer tasks, with editing conditions converted into different proxies accordingly. The editing effects are added upon the input image by blending the corresponding proxy features within the hairstyle or hair color feature spaces. Besides the unprecedented user interaction mode support, quantitative and qualitative experiments demonstrate the superiority of HairCLIPv2 in terms of editing effects, irrelevant attribute preservation and visual naturalness. Our code is available at urlhttps://github.com/wty-ustc/HairCLIPv2.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 41 of its 55 references that are in the map. First posted on arXiv 16 Oct 2023.

Builds on

41 of 55 references.

References · 41

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  6. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  7. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  8. 2017Improved Training of Wasserstein GANscited by 2,235
  9. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  10. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  11. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  12. 2019VL-BERT: Pre-training of Generic Visual-Linguistic Representationscited by 954
29 more
  1. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 927
  2. 2021Florence: A New Foundation Model for Computer Visioncited by 804
  3. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  4. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 695
  5. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  6. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  7. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 642
  8. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 544
  9. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 525
  10. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  11. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  12. 2019SEAN: Image Synthesis with Semantic Region-Adaptive Normalizationcited by 253
  13. 2022MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretrainingcited by 187
  14. 2020Editing in Style: Uncovering the Local Semantics of GANscited by 183
  15. 2022OmniVL:One Foundation Model for Image-Language and Video-Language Taskscited by 143
  16. 2020A U-Net Based Discriminator for Generative Adversarial Networkscited by 128
  17. 2019SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Colorcited by 106
  18. 2020Improved StyleGAN Embedding: Where are the Good Latents?cited by 88
  19. 2021HairCLIP: Design Your Hair by Text and Reference Imagecited by 80
  20. 2020Efficient Semantic Image Synthesis via Class-Adaptive Normalizationcited by 58
  21. 2023Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimizationcited by 55
  22. 2021Diverse Semantic Image Synthesis via Probability Distribution Modelingcited by 49
  23. 2022X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusioncited by 49
  24. 2021E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversioncited by 33
  25. 2021LOHO: Latent Optimization of Hairstyles via Orthogonalizationcited by 30
  26. 2019A Characteristic Function Approach to Deep Implicit Generative Modelingcited by 26
  27. 2020On Noise Injection in Generative Adversarial Networkscited by 19
  28. 2022Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignmentcited by 16
  29. 2022Principled Knowledge Extrapolation with GANscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 5; 2026: 6.

17 papers.

Sort:

By area:

  1. 2025FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editingcited by 22
  2. 2024Enhancing MMDiT-Based Text-to-Image Models for Similar Subject Generationcited by 11
  3. 2024HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approachcited by 10
  4. 2024Reference-Based 3D-Aware Image Editing with Triplanescited by 9
  5. 20253DGH: 3D Head Generation with Composable Hair and Facecited by 8
  6. 2025Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scalingcited by 4
  7. 2024Diverse and Lifespan Facial Age Transformation Synthesis with Identity Variation Rationality Metriccited by 3
  8. 2024HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusioncited by 3
  9. 2025Stable-Hair v2: Real-World Hair Transfer via Multiple-View Diffusion Modelcited by 2
  10. 2026The Devil Is in the Leakage: A Disentangled Dual-Purification Framework for High-Fidelity Hairstyle Transfercited by 2
  11. 2024A Reference-Based 3D Semantic-Aware Framework for Accurate Local Facial Attribute Editingcited by 0
  12. 2025HairShifter: Consistent and High-Fidelity Video Hair Transfer via Anchor-Guided Animationcited by 0
5 more
  1. 2026UniBioTransfer: A Unified Framework for Multiple Biometrics Transfercited by 0
  2. 2026COSY: Compositional 3DGS Synthesis for Disentangled Human Head Editingcited by 0
  3. 2026HairPort: In-context 3D-aware Hair Import and Transfer for Imagescited by 0
  4. 2026H-Adapter: Pose-Robust Hairstyle Transfer via Attention-Derived, Source-Aligned Hair Maskscited by 0
  5. 2026Detangled: A Framework for Creating, Editing, and Inferencing Feature Rich Hair Strandscited by 0