# MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing

arXiv: https://arxiv.org/abs/2010.16417 · HTML: https://mlsanity.com/paper/2010.16417/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2020.

## Built on by (most cited first, 18 of 18)

- [CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directions](https://mlsanity.com/paper/2112.05219/) (2021)
- [Diverse Semantic Image Synthesis via Probability Distribution Modeling](https://mlsanity.com/paper/2103.06878/) (2021)
- [Reduce Information Loss in Transformers for Pluralistic Image Inpainting](https://mlsanity.com/paper/2205.05076/) (2022)
- [HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling](https://mlsanity.com/paper/2303.02700/) (2023)
- [Rewriting Geometric Rules of a GAN](https://mlsanity.com/paper/2207.14288/) (2022)
- [MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation](https://mlsanity.com/paper/2111.01048/) (2021)
- [Barbershop: GAN-based Image Compositing using Segmentation Masks](https://mlsanity.com/paper/2106.01505/) (2021)
- [ManiCLIP: Multi-Attribute Face Manipulation from Text](https://mlsanity.com/paper/2210.00445/) (2022)
- [DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing](https://mlsanity.com/paper/2109.10737/) (2021)
- [StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer](https://mlsanity.com/paper/2304.02744/) (2023)
- [DisUnknown: Distilling Unknown Factors for Disentanglement Learning](https://mlsanity.com/paper/2109.08090/) (2021)
- [A comprehensive survey on semantic facial attribute editing using generative adversarial networks](https://mlsanity.com/paper/2205.10587/) (2022)
- [Guiding Users to Where to Give Color Hints for Efficient Interactive Sketch Colorization via Unsupervised Region Prioritization](https://mlsanity.com/paper/2210.14270/) (2022)
- [SketchHairSalon: Deep Sketch-based Hair Image Synthesis](https://mlsanity.com/paper/2109.07874/) (2021)
- [MixSyn: Learning Composition and Style for Multi-Source Image Synthesis](https://mlsanity.com/paper/2111.12705/) (2021)
- [Real-time Virtual-Try-On from a Single Example Image through Deep Inverse Graphics and Learned Differentiable Renderers](https://mlsanity.com/paper/2205.06305/) (2022)
- [gCoRF: Generative Compositional Radiance Fields](https://mlsanity.com/paper/2210.17344/) (2022)
- [Efficient Hair Style Transfer with Generative Adversarial Networks](https://mlsanity.com/paper/2210.12524/) (2022)

## Abstract (arXiv)

Despite the recent success of face image generation with GANs, conditional hair editing remains challenging due to the under-explored complexity of its geometry and appearance. In this paper, we present MichiGAN (Multi-Input-Conditioned Hair Image GAN), a novel conditional image generation method for interactive portrait hair manipulation. To provide user control over every major hair visual factor, we explicitly disentangle hair into four orthogonal attributes, including shape, structure, appearance, and background. For each of them, we design a corresponding condition module to represent, process, and convert user inputs, and modulate the image generation pipeline in ways that respect the natures of different visual attributes. All these condition modules are integrated with the backbone generator to form the final end-to-end network, which allows fully-conditioned hair generation from multiple user inputs. Upon it, we also build an interactive portrait hair editing system that enables straightforward manipulation of hair by projecting intuitive and high-level user inputs such as painted masks, guiding strokes, or reference photos to well-defined condition representations. Through extensive experiments and evaluations, we demonstrate the superiority of our method regarding both result quality and user controllability. The code is available at https://github.com/tzt101/MichiGAN.