Fine-Grained Expression Manipulation Via Structured Latent Space

Fine-grained facial expression manipulation is a challenging problem, as fine-grained expression details are difficult to be captured. Most existing expression manipulation methods resort to discrete expression labels, which mainly edit global expressions and ignore the manipulation of fine details....

Full description

Saved in:
Bibliographic Details
Main Authors: Tang, Junshu, Shao, Zhiwen, Ma, Lizhuang
Format: Conference Proceeding
Language:English
Subjects:
Aerospace electronics
continuous expression
Face
Fine-grained expression manipulation
Gallium nitride
Generative adversarial networks
Gold
Interpolation
Shape
structured latent space
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Fine-grained facial expression manipulation is a challenging problem, as fine-grained expression details are difficult to be captured. Most existing expression manipulation methods resort to discrete expression labels, which mainly edit global expressions and ignore the manipulation of fine details. To tackle this limitation, we propose an end-to-end expression-guided generative adversarial network (EGGAN), which utilizes structured latent codes and continuous expression labels as input to generate images with expected expressions. Specifically, we adopt an adversarial autoencoder to map a source image into a structured latent space. Then, given the source latent code and the target expression label, we employ a conditional GAN to generate a new image with the target expression. Moreover, we introduce a perceptual loss and a multi-scale structural similarity loss to preserve identity and global shape during generation. Extensive experiments show that our method can manipulate fine-grained expressions, and generate continuous intermediate expressions between source and target expressions.
ISSN:1945-788X
DOI:10.1109/ICME46284.2020.9102852