mlsanityData to 7 Oct 2026

LOHO: Latent Optimization of Hairstyles via Orthogonalization

arXiv 2103.03891 ↗First posted 5 Mar 2021cs.CV cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Hairstyle transfer is challenging due to hair structure differences in the source and target hair. Therefore, we propose Latent Optimization of Hairstyles via Orthogonalization (LOHO), an optimization-based approach using GAN inversion to infill missing hair structure details in latent space during hairstyle transfer. Our approach decomposes hair into three attributes: perceptual structure, appearance, and style, and includes tailored losses to model each of these attributes independently. Furthermore, we propose two-stage optimization and gradient orthogonalization to enable disentangled latent space optimization of our hair attributes. Using LOHO for latent space manipulation, users can synthesize novel photorealistic images by manipulating hair attributes either individually or jointly, transferring the desired attributes from reference hairstyles. LOHO achieves a superior FID compared with the current state-of-the-art (SOTA) for hairstyle transfer. Additionally, LOHO preserves the subject's identity comparably well according to PSNR and SSIM when compared to SOTA image embedding pipelines. Code is available at https://github.com/dukebw/LOHO.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 32 of its 43 references that are in the map. First posted on arXiv 5 Mar 2021.

Builds on

32 of 43 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  9. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  11. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  12. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
20 more
  1. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  2. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  3. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  4. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  5. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  6. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  7. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 524
  8. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  9. 2018Video-to-Video Synthesiscited by 388
  10. 2019Image2StyleGAN++: How to Edit the Embedded Images?cited by 356
  11. 2018Everybody Dance Nowcited by 313
  12. 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
  13. 2019Few-shot Video-to-Video Synthesiscited by 196
  14. 2020Hierarchical Multi-Scale Attention for Semantic Segmentationcited by 183
  15. 2020Adversarial Latent Autoencoderscited by 155
  16. 2020Neural Head Reenactment with Latent Pose Descriptorscited by 106
  17. 2019SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Colorcited by 105
  18. 2019Graphonomy: Universal Human Parsing via Graph Transfer Learningcited by 81
  19. 2017Perceptual Generative Adversarial Networks for Small Object Detectioncited by 76
  20. 2020Collaborative Learning for Faster StyleGAN Embeddingcited by 65

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 10; 2023: 6; 2024: 6; 2025: 2; 2026: 2.

30 papers.

Sort:

By area:

  1. 2021HairCLIP: Design Your Hair by Text and Reference Imagecited by 79
  2. 2022Fine-Grained Face Swapping via Regional GAN Inversioncited by 67
  3. 2023RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatarscited by 45
  4. 2024Stable-Hair: Real-World Hair Transfer via Diffusion Modelcited by 34
  5. 2021StyleFusion: A Generative Model for Disentangling Spatial Segmentscited by 28
  6. 2022Temporally Consistent Semantic Video Editingcited by 28
  7. 2023HairCLIPv2: Unifying Hair Editing via Proxy Feature Blendingcited by 17
  8. 2022Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignmentcited by 16
  9. 2024Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Modelscited by 15
  10. 2021Barbershop: GAN-based Image Compositing using Segmentation Maskscited by 14
  11. 2024Diffusion-driven GAN Inversion for Multi-Modal Face Image Generationcited by 12
  12. 2022Exploring Gradient-based Multi-directional Controls in GANscited by 10
18 more
  1. 2024HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approachcited by 10
  2. 2022HairFIT: Pose-Invariant Hairstyle Transfer via Flow-based Hair Alignment and Semantic-Region-Aware Inpaintingcited by 9
  3. 2022IntereStyle: Encoding an Interest Region for Robust StyleGAN Inversioncited by 8
  4. 2022ManiCLIP: Multi-Attribute Face Manipulation from Textcited by 8
  5. 2023E4S: Fine-grained Face Swapping via Editing With Regional GAN Inversioncited by 8
  6. 2023StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfercited by 7
  7. 2024SegTalker: Segmentation-based Talking Face Generation with Mask-guided Local Editingcited by 5
  8. 2024HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusioncited by 3
  9. 2022Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Rendererscited by 2
  10. 2022gCoRF: Generative Compositional Radiance Fieldscited by 2
  11. 2025Stable-Hair v2: Real-World Hair Transfer via Multiple-View Diffusion Modelcited by 2
  12. 2023HyperEditor: Achieving Both Authenticity and Cross-Domain Capability in Image Editing via Hypernetworkscited by 1
  13. 2021Face sketch to photo translation using generative adversarial networkscited by 0
  14. 2022Efficient Hair Style Transfer with Generative Adversarial Networkscited by 0
  15. 2023Trained Latent Space Navigation to Prevent Lack of Photorealism in Generated Images on Style-based Modelscited by 0
  16. 2025HairShifter: Consistent and High-Fidelity Video Hair Transfer via Anchor-Guided Animationcited by 0
  17. 2026HairPort: In-context 3D-aware Hair Import and Transfer for Imagescited by 0
  18. 2026H-Adapter: Pose-Robust Hairstyle Transfer via Attention-Derived, Source-Aligned Hair Maskscited by 0