# HairNet: Single-View Hair Reconstruction using Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1806.07467 · HTML: https://mlsanity.com/paper/1806.07467/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jun 2018.

## Built on by (most cited first, 4 of 4)

- [NeuralHDHair: Automatic High-fidelity Hair Modeling from a Single Image Using Implicit Neural Representations](https://mlsanity.com/paper/2205.04175/) (2022)
- [Single-Camera 3D Head Fitting for Mixed Reality Clinical Applications](https://mlsanity.com/paper/2109.02740/) (2021)
- [SketchHairSalon: Deep Sketch-based Hair Image Synthesis](https://mlsanity.com/paper/2109.07874/) (2021)
- [GeomHair: Reconstruction of Hair Strands from Colorless 3D Scans](https://mlsanity.com/paper/2505.05376/) (2025)

## Abstract (arXiv)

We introduce a deep learning-based method to generate full 3D hair geometry from an unconstrained image. Our method can recover local strand details and has real-time performance. State-of-the-art hair modeling techniques rely on large hairstyle collections for nearest neighbor retrieval and then perform ad-hoc refinement. Our deep learning approach, in contrast, is highly efficient in storage and can run 1000 times faster while generating hair with 30K strands. The convolutional neural network takes the 2D orientation field of a hair image as input and generates strand features that are evenly distributed on the parameterized 2D scalp. We introduce a collision loss to synthesize more plausible hairstyles, and the visibility of each strand is also used as a weight term to improve the reconstruction accuracy. The encoder-decoder architecture of our network naturally provides a compact and continuous representation for hairstyles, which allows us to interpolate naturally between hairstyles. We use a large set of rendered synthetic hair models to train our network. Our method scales to real images because an intermediate 2D orientation field, automatically calculated from the real image, factors out the difference between synthetic and real hairs. We demonstrate the effectiveness and robustness of our method on a wide range of challenging real Internet pictures and show reconstructed hair sequences from videos.