DeepFaceEditing : Deep face generation and editing with disentangled geometry and appearance control

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

View graph of relations

Author(s)

  • Shu-Yu CHEN
  • Feng-Lin LIU
  • Yu-Kun LAI
  • Paul L. ROSIN
  • Chunpeng LI
  • Lin GAO

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number90
Journal / PublicationACM Transactions on Graphics
Volume40
Issue number4
Online published19 Jul 2021
Publication statusPublished - Aug 2021

Abstract

Recent facial image synthesis methods have been mainly based on conditional generative models. Sketch-based conditions can effectively describe the geometry of faces, including the contours of facial components, hair structures, as well as salient edges (e.g., wrinkles) on face surfaces but lack effective control of appearance, which is influenced by color, material, lighting condition, etc. To have more control of generated results, one possible approach is to apply existing disentangling works to disentangle face images into geometry and appearance representations. However, existing disentangling methods are not optimized for human face editing, and cannot achieve fine control of facial details such as wrinkles. To address this issue, we propose DeepFaceEditing, a structured disentanglement framework specifically designed for face images to support face generation and editing with disentangled control of geometry and appearance. We adopt a local-to-global approach to incorporate the face domain knowledge: local component images are decomposed into geometry and appearance representations, which are fused consistently using a global fusion module to improve generation quality. We exploit sketches to assist in extracting a better geometry representation, which also supports intuitive geometry editing via sketching. The resulting method can either extract the geometry and appearance representations from face images, or directly extract the geometry representation from face sketches. Such representations allow users to easily edit and synthesize face images, with decoupled control of their geometry and appearance. Both qualitative and quantitative evaluations show the superior detail and appearance control abilities of our method compared to state-of-the-art methods.

Research Area(s)

  • deep image generation, face editing, image disentangling, sketch-based interfaces

Citation Format(s)

DeepFaceEditing : Deep face generation and editing with disentangled geometry and appearance control. / CHEN, Shu-Yu; LIU, Feng-Lin; LAI, Yu-Kun; ROSIN, Paul L.; LI, Chunpeng; FU, Hongbo; GAO, Lin.

In: ACM Transactions on Graphics, Vol. 40, No. 4, 90, 08.2021.

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