mlsanityData to 7 Oct 2026

Perm: A Parametric Representation for Multi-Style 3D Hair Modeling

arXiv 2407.19451 ↗First posted 28 Jul 2024cs.CV cs.GRcited by 21

Not on the map. Why?

Abstract (arXiv)

We present Perm, a learned parametric representation of human 3D hair designed to facilitate various hair-related applications. Unlike previous work that jointly models the global hair structure and local curl patterns, we propose to disentangle them using a PCA-based strand representation in the frequency domain, thereby allowing more precise editing and output control. Specifically, we leverage our strand representation to fit and decompose hair geometry textures into low- to high-frequency hair structures, termed guide textures and residual textures, respectively. These decomposed textures are later parameterized with different generative models, emulating common stages in the hair grooming process. We conduct extensive experiments to validate the architecture design of Perm, and finally deploy the trained model as a generic prior to solve task-agnostic problems, further showcasing its flexibility and superiority in tasks such as single-view hair reconstruction, hairstyle editing, and hair-conditioned image generation. More details can be found on our project page: https://cs.yale.edu/homes/che/projects/perm/.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 34 of its 89 references that are in the map. First posted on arXiv 28 Jul 2024.

Builds on

34 of 89 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2023Visual Instruction Tuningcited by 7,792
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2017Squeeze-and-Excitation Networkscited by 4,763
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  10. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  11. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  12. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
22 more
  1. 2020Encoding in Style: a StyleGAN Encoder for Image-to-Image Translationcited by 727
  2. 2019Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?cited by 675
  3. 2018Which Training Methods for GANs do actually Converge?cited by 672
  4. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  5. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 310
  6. 2020State of the Art on Neural Renderingcited by 276
  7. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
  8. 2024GaussianHair: Hair Modeling and Rendering with Light-aware Gaussianscited by 48
  9. 2023Neural Haircut: Prior-Guided Strand-Based Hair Reconstructioncited by 43
  10. 2022Neural Strands: Learning Hair Geometry and Appearance from Multi-View Imagescited by 39
  11. 2023HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modelingcited by 35
  12. 2022NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representationscited by 31
  13. 2022NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animationcited by 30
  14. 2021HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance Capturecited by 29
  15. 2023HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstylescited by 29
  16. 2023GroomGen: A High-Quality Generative Hair Model Using Hierarchical Latent Representationscited by 28
  17. 2019DeepSketchHair: Deep Sketch-based 3D Hair Modelingcited by 24
  18. 2024MonoHair: High-Fidelity Hair Modeling from a Monocular Videocited by 24
  19. 2023RaBit: Parametric Modeling of 3D Biped Cartoon Characters with a Topological-consistent Datasetcited by 18
  20. 2018Video to Fully Automatic 3D Hair Modelcited by 12
  21. 2024Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-training via Differentiable Rendering of Line Segmentscited by 11
  22. 2023A Local Appearance Model for Volumetric Capture of Diverse Hairstylecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 10.

21 papers.

Sort:

By area:

  1. 2025DiffLocks: Generating 3D Hair from a Single Image using Diffusion Modelscited by 15
  2. 2024Quaffure: Real-Time Quasi-Static Neural Hair Simulationcited by 10
  3. 20253DGH: 3D Head Generation with Composable Hair and Facecited by 8
  4. 2025Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatarscited by 8
  5. 2024StrandHead: Text to Hair-Disentangled 3D Head Avatars Using Human-Centric Priorscited by 3
  6. 2025Neuralocks: Real-Time Dynamic Neural Hair Simulationcited by 3
  7. 2025CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modelingcited by 3
  8. 2026PhysHead: Simulation-Ready Gaussian Head Avatarscited by 2
  9. 2026OmniFit: Multi-modal 3D Body Fitting via Scale-agnostic Dense Landmark Predictioncited by 2
  10. 2025GeomHair: Reconstruction of Hair Strands from Colorless 3D Scanscited by 1
  11. 2025HairFormer: Transformer-Based Dynamic Neural Hair Simulationcited by 1
  12. 2025StrandDesigner: Towards Practical Strand Generation with Sketch Guidancecited by 1
9 more
  1. 2025DGH: Dynamic Gaussian Haircited by 1
  2. 2026DiffProxy: Multi-View Human Mesh Recovery via Diffusion-Generated Dense Proxiescited by 1
  3. 2026CGHair: Compact Gaussian Hair Reconstruction with Card Clusteringcited by 1
  4. 2026FHAvatar: Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head Avatar from Few Casual Capturescited by 0
  5. 2026HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesiscited by 0
  6. 2026HairLRM: Strand-based Hair Modeling via Large Reconstruction Modelscited by 0
  7. 2026Head Avatars with Dynamic Explicit Haircited by 0
  8. 2026HairCS: Reconstructing Strand-Based Hair from Hair Cardscited by 0
  9. 2026FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasetscited by 0