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

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

12 Scopus Citations
View graph of relations

Author(s)

  • Zhentao TAN
  • Menglei CHAI
  • Dongdong CHEN
  • Qi CHU
  • Lu YUAN
  • Sergey TULYAKOV
  • Nenghai YU

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number95
Journal / PublicationACM Transactions on Graphics
Volume39
Issue number4
Publication statusPublished - Jul 2020

Abstract

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.

Research Area(s)

  • conditional hair image generation, generative adversarial networks, interactive portrait editing

Bibliographic Note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Citation Format(s)

MichiGAN : Multi-Input-Conditioned Hair Image Generation for Portrait Editing. / TAN, Zhentao; CHAI, Menglei; CHEN, Dongdong; LIAO, Jing; CHU, Qi; YUAN, Lu; TULYAKOV, Sergey; YU, Nenghai.

In: ACM Transactions on Graphics, Vol. 39, No. 4, 95, 07.2020.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review