mlsanityData to 14 Oct 2026

Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction

arXiv 2306.05872 ↗First posted 9 Jun 2023cs.CV cs.GRcited by 43

Not on the map. Why?

Abstract (arXiv)

Generating realistic human 3D reconstructions using image or video data is essential for various communication and entertainment applications. While existing methods achieved impressive results for body and facial regions, realistic hair modeling still remains challenging due to its high mechanical complexity. This work proposes an approach capable of accurate hair geometry reconstruction at a strand level from a monocular video or multi-view images captured in uncontrolled lighting conditions. Our method has two stages, with the first stage performing joint reconstruction of coarse hair and bust shapes and hair orientation using implicit volumetric representations. The second stage then estimates a strand-level hair reconstruction by reconciling in a single optimization process the coarse volumetric constraints with hair strand and hairstyle priors learned from the synthetic data. To further increase the reconstruction fidelity, we incorporate image-based losses into the fitting process using a new differentiable renderer. The combined system, named Neural Haircut, achieves high realism and personalization of the reconstructed hairstyles.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). Builds on 48 of its 82 references that are in the map. First posted on arXiv 9 Jun 2023.

Builds on

48 of 82 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2018Neural Ordinary Differential Equationscited by 3,779
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  6. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  8. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  9. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  10. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  11. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  12. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
36 more
  1. 2017Deep Image Priorcited by 1,098
  2. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  3. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  4. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  5. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  6. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  7. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  8. 2017How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)cited by 525
  9. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
  10. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 467
  11. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  12. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  13. 2016Convolutional Pose Machinescited by 325
  14. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  15. 2017Hand Keypoint Detection in Single Images using Multiview Bootstrappingcited by 231
  16. 2021I M Avatar: Implicit Morphable Head Avatars from Videoscited by 231
  17. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  18. 2021Neural Head Avatars from Monocular RGB Videoscited by 213
  19. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 212
  20. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  21. 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 184
  22. 2019Neural Volumes: Learning Dynamic Renderable Volumes from Imagescited by 173
  23. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
  24. 2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
  25. 2021Improving neural implicit surfaces geometry with patch warpingcited by 137
  26. 2020MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decompositioncited by 127
  27. 2022Realistic One-shot Mesh-based Head Avatarscited by 119
  28. 2021H3D-Net: Few-Shot High-Fidelity 3D Head Reconstructioncited by 81
  29. 2022KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypointscited by 77
  30. 2022Learning Neural Parametric Head Modelscited by 73
  31. 2022Neural Strands: Learning Hair Geometry and Appearance from Multi-View Imagescited by 40
  32. 2022NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representationscited by 32
  33. 2022NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animationcited by 30
  34. 2021HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance Capturecited by 29
  35. 2021CDGNet: Class Distribution Guided Network for Human Parsingcited by 26
  36. 2021Prior-Guided Multi-View 3D Head Reconstructioncited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 13; 2025: 15; 2026: 10.

43 papers.

Sort:

By area:

  1. 2023TADA! Text to Animatable Digital Avatarscited by 110
  2. 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
  3. 2024GaussianHair: Hair Modeling and Rendering with Light-aware Gaussianscited by 48
  4. 2023Learning Disentangled Avatars with Hybrid 3D Representationscited by 44
  5. 2024Human Hair Reconstruction with Strand-Aligned 3D Gaussianscited by 36
  6. 2023HHAvatar: Gaussian Head Avatar with Dynamic Hairscited by 35
  7. 2023HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstylescited by 30
  8. 2024MonoHair: High-Fidelity Hair Modeling from a Monocular Videocited by 24
  9. 2024Perm: A Parametric Representation for Multi-Style 3D Hair Modelingcited by 22
  10. 2025DiffLocks: Generating 3D Hair from a Single Image using Diffusion Modelscited by 16
  11. 2024SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatarscited by 15
  12. 2024Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-training via Differentiable Rendering of Line Segmentscited by 11
31 more
  1. 2024Quaffure: Real-Time Quasi-Static Neural Hair Simulationcited by 10
  2. 2024Towards Unified 3D Hair Reconstruction from Single-View Portraitscited by 9
  3. 2024SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothingcited by 9
  4. 2025Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatarscited by 9
  5. 2024PEGASUS: Personalized Generative 3D Avatars with Composable Attributescited by 7
  6. 2025HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatarscited by 7
  7. 2024Hairmony: Fairness-aware hairstyle classificationcited by 5
  8. 20244DPV: 4D Pet from Videos by Coarse-to-Fine Non-Rigid Radiance Fieldscited by 5
  9. 2024StrandHead: Text to Hair-Disentangled 3D Head Avatars Using Human-Centric Priorscited by 4
  10. 2025CHARM: Control-point-based 3D Anime Hairstyle Auto-Regressive Modelingcited by 4
  11. 2026NeuralFur: Animal Fur Reconstruction From Multi-View Imagescited by 4
  12. 2025Neuralocks: Real-Time Dynamic Neural Hair Simulationcited by 3
  13. 2025SRM-Hair: Single Image Head Mesh Reconstruction via 3D Morphable Haircited by 2
  14. 2025StrandDesigner: Towards Practical Strand Generation with Sketch Guidancecited by 2
  15. 2025HairGS: Hair Strand Reconstruction based on 3D Gaussian Splattingcited by 2
  16. 2025DGH: Dynamic Gaussian Haircited by 2
  17. 2026PhysHead: Simulation-Ready Gaussian Head Avatarscited by 2
  18. 2025GeomHair: Reconstruction of Hair Strands from Colorless 3D Scanscited by 1
  19. 2025VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesiscited by 1
  20. 2025HairFormer: Transformer-Based Dynamic Neural Hair Simulationcited by 1
  21. 2026HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraitscited by 1
  22. 2026CGHair: Compact Gaussian Hair Reconstruction with Card Clusteringcited by 1
  23. 2026MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulationcited by 1
  24. 2025Unsupervised 3D Braided Hair Reconstruction from a Single-View Imagecited by 0
  25. 2025Capture Stage Matting: Challenges, Approaches, and Solutions for Offline and Real-Time Processingcited by 0
  26. 2025PanoHair: Detailed Hair Strand Synthesis on Volumetric Headscited by 0
  27. 2026FHAvatar: Fast and High-Fidelity Reconstruction of Face-and-Hair Composable 3D Head Avatar from Few Casual Capturescited by 0
  28. 2026EfficientMonoHair: Fast Strand-Level Reconstruction from Monocular Video via Multi-View Direction Fusioncited by 0
  29. 2026Wispy to Voluminous: Prior-free Multi-view Capture of Strand-level Facial Haircited by 0
  30. 2026Head Avatars with Dynamic Explicit Haircited by 0
  31. 2026FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasetscited by 0