SRM-Hair: Single Image Head Mesh Reconstruction via 3D Morphable Hair
Not on the map. Why?
Abstract (arXiv)
3D Morphable Models (3DMMs) have played a pivotal role as a fundamental representation or initialization for 3D avatar animation and reconstruction. However, extending 3DMMs to hair remains challenging due to the difficulty of enforcing vertex-level consistent semantic meaning across hair shapes. This paper introduces a novel method, Semantic-consistent Ray Modeling of Hair (SRM-Hair), for making 3D hair morphable and controlled by coefficients. The key contribution lies in semantic-consistent ray modeling, which extracts ordered hair surface vertices and exhibits notable properties such as additivity for hairstyle fusion, adaptability, flipping, and thickness modification. We collect a dataset of over 250 high-fidelity real hair scans paired with 3D face data to serve as a prior for the 3D morphable hair. Based on this, SRM-Hair can reconstruct a hair mesh combined with a 3D head from a single image. Note that SRM-Hair produces an independent hair mesh, facilitating applications in virtual avatar creation, realistic animation, and high-fidelity hair rendering. Both quantitative and qualitative experiments demonstrate that SRM-Hair achieves state-of-the-art performance in 3D mesh reconstruction. Our project is available at https://github.com/wang-zidu/SRM-Hair
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 49 of its 72 references that are in the map. First posted on arXiv 8 Mar 2025.
Builds on
49 of 72 references.
References · 49
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
- 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
- 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
- 2018Open3D: A Modern Library for 3D Data Processingcited by 721
- 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 689
- 2019MediaPipe: A Framework for Building Perception Pipelinescited by 583
- 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
- 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 482
37 more
- 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 477
- 2020Modular Primitives for High-Performance Differentiable Renderingcited by 441
- 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
- 20193D Morphable Face Models -- Past, Present and Futurecited by 270
- 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 260
- 2023GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussianscited by 260
- 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
- 2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
- 2018Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Networkcited by 195
- 2021Pixel Codec Avatarscited by 127
- 2023Relightable Gaussian Codec Avatarscited by 127
- 2019Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Researchcited by 98
- 2022FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Datasetcited by 98
- 2024SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesiscited by 84
- 2021H3D-Net: Few-Shot High-Fidelity 3D Head Reconstructioncited by 81
- 2022Learning Neural Parametric Head Modelscited by 73
- 2024GaussianHair: Hair Modeling and Rendering with Light-aware Gaussianscited by 48
- 2023Learning Disentangled Avatars with Hybrid 3D Representationscited by 44
- 2023Neural Haircut: Prior-Guided Strand-Based Hair Reconstructioncited by 43
- 20233D Face Reconstruction with the Geometric Guidance of Facial Part Segmentationcited by 38
- 2024MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editingcited by 38
- 2024Human Hair Reconstruction with Strand-Aligned 3D Gaussianscited by 36
- 2023MonoNPHM: Dynamic Head Reconstruction from Monocular Videoscited by 35
- 2022REALY: Rethinking the Evaluation of 3D Face Reconstructioncited by 33
- 2022NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representationscited by 32
- 2024Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Videocited by 25
- 2024MonoHair: High-Fidelity Hair Modeling from a Monocular Videocited by 24
- 2022Towards 3D Face Reconstruction in Perspective Projection: Estimating 6DoF Face Pose from Monocular Imagecited by 9
- 2024Towards Unified 3D Hair Reconstruction from Single-View Portraitscited by 9
- 2023Implicit Shape and Appearance Priors for Few-Shot Full Head Reconstructioncited by 8
- 2025Disentangled Clothed Avatar Generation with Layered Representationcited by 7
- 2025LUCAS: Layered Universal Codec Avatarscited by 7
- 2023HeadCraft: Modeling High-Detail Shape Variations for Animated 3DMMscited by 5
- 2024Semantic Human Mesh Reconstruction with Texturescited by 5
- 2024ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Samplingcited by 5
- 2024S2TD-Face: Reconstruct a Detailed 3D Face with Controllable Texture from a Single Sketchcited by 5
- 2025PrismAvatar: Real-time animated 3D neural head avatars on edge devicescited by 2
Built on by
Citing papers per year: 2025: 2.
2 papers.