# Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-training via Differentiable Rendering of Line Segments

arXiv: https://arxiv.org/abs/2403.17496 · HTML: https://mlsanity.com/paper/2403.17496/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 70 references that are in the map.
- First posted on arXiv 26 Mar 2024.

## Builds on (most cited first, 21 of 21)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Modular Primitives for High-Performance Differentiable Rendering](https://mlsanity.com/paper/2011.03277/) (2020)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [Mixture of Volumetric Primitives for Efficient Neural Rendering](https://mlsanity.com/paper/2103.01954/) (2021)
- [Differentiable Surface Splatting for Point-based Geometry Processing](https://mlsanity.com/paper/1906.04173/) (2019)
- [H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction](https://mlsanity.com/paper/2107.12512/) (2021)
- [GaussianHair: Hair Modeling and Rendering with Light-aware Gaussians](https://mlsanity.com/paper/2402.10483/) (2024)
- [Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction](https://mlsanity.com/paper/2306.05872/) (2023)
- [Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images](https://mlsanity.com/paper/2207.14067/) (2022)
- [HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling](https://mlsanity.com/paper/2303.02700/) (2023)
- [NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representations](https://mlsanity.com/paper/2205.04175/) (2022)
- [NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation](https://mlsanity.com/paper/2212.00613/) (2022)
- [HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles](https://mlsanity.com/paper/2312.11666/) (2023)
- [HVH: Learning a Hybrid Neural Volumetric Representation for Dynamic Hair Performance Capture](https://mlsanity.com/paper/2112.06904/) (2021)
- [GroomGen: A High-Quality Generative Hair Model Using Hierarchical Latent Representations](https://mlsanity.com/paper/2311.02062/) (2023)
- [Differentiable Surface Rendering via Non-Differentiable Sampling](https://mlsanity.com/paper/2108.04886/) (2021)
- [CDGNet: Class Distribution Guided Network for Human Parsing](https://mlsanity.com/paper/2111.14173/) (2021)
- [DeepSketchHair: Deep Sketch-based 3D Hair Modeling](https://mlsanity.com/paper/1908.07198/) (2019)
- [Dressi: A Hardware-Agnostic Differentiable Renderer with Reactive Shader Packing and Soft Rasterization](https://mlsanity.com/paper/2204.01386/) (2022)

## Built on by (most cited first, 11 of 11)

- [Perm: A Parametric Representation for Multi-Style 3D Hair Modeling](https://mlsanity.com/paper/2407.19451/) (2024)
- [DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models](https://mlsanity.com/paper/2505.06166/) (2025)
- [Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars](https://mlsanity.com/paper/2509.01469/) (2025)
- [StrandHead: Text to Hair-Disentangled 3D Head Avatars Using Human-Centric Priors](https://mlsanity.com/paper/2412.11586/) (2024)
- [NeuralFur: Animal Fur Reconstruction From Multi-View Images](https://mlsanity.com/paper/2601.12481/) (2026)
- [HairGS: Hair Strand Reconstruction based on 3D Gaussian Splatting](https://mlsanity.com/paper/2509.07774/) (2025)
- [DGH: Dynamic Gaussian Hair](https://mlsanity.com/paper/2512.17094/) (2025)
- [PhysHead: Simulation-Ready Gaussian Head Avatars](https://mlsanity.com/paper/2604.06467/) (2026)
- [GeomHair: Reconstruction of Hair Strands from Colorless 3D Scans](https://mlsanity.com/paper/2505.05376/) (2025)
- [Wispy to Voluminous: Prior-free Multi-view Capture of Strand-level Facial Hair](https://mlsanity.com/paper/2606.08041/) (2026)
- [Detangled: A Framework for Creating, Editing, and Inferencing Feature Rich Hair Strands](https://mlsanity.com/paper/2607.09811/) (2026)

## Abstract (arXiv)

In the film and gaming industries, achieving a realistic hair appearance typically involves the use of strands originating from the scalp. However, reconstructing these strands from observed surface images of hair presents significant challenges. The difficulty in acquiring Ground Truth (GT) data has led state-of-the-art learning-based methods to rely on pre-training with manually prepared synthetic CG data. This process is not only labor-intensive and costly but also introduces complications due to the domain gap when compared to real-world data. In this study, we propose an optimization-based approach that eliminates the need for pre-training. Our method represents hair strands as line segments growing from the scalp and optimizes them using a novel differentiable rendering algorithm. To robustly optimize a substantial number of slender explicit geometries, we introduce 3D orientation estimation utilizing global optimization, strand initialization based on Laplace's equation, and reparameterization that leverages geometric connectivity and spatial proximity. Unlike existing optimization-based methods, our method is capable of reconstructing internal hair flow in an absolute direction. Our method exhibits robust and accurate inverse rendering, surpassing the quality of existing methods and significantly improving processing speed.