Please use this identifier to cite or link to this item:
Title: LEED : label-free expression editing via disentanglement
Authors: Wu, Rongliang
Lu, Shijian
Keywords: Engineering
Issue Date: 2020
Source: Wu, R., & Lu, S. (2020). LEED : label-free expression editing via disentanglement. Proceedings of the European Conference on Computer Vision, 12357 LNCS, 781-798. doi:10.1007/978-3-030-58610-2_46
Project: #001531-00001
Abstract: Recent studies on facial expression editing have obtained very promising progress. On the other hand, existing methods face the constraint of requiring a large amount of expression labels which are often expensive and time-consuming to collect. This paper presents an innovative label-free expression editing via disentanglement (LEED) framework that is capable of editing the expression of both frontal and profile facial images without requiring any expression label. The idea is to disentangle the identity and expression of a facial image in the expression manifold, where the neutral face captures the identity attribute and the displacement between the neutral image and the expressive image captures the expression attribute. Two novel losses are designed for optimal expression disentanglement and consistent synthesis, including a mutual expression information loss that aims to extract pure expression-related features and a siamese loss that aims to enhance the expression similarity between the synthesized image and the reference image. Extensive experiments over two public facial expression datasets show that LEED achieves superior facial expression editing qualitatively and quantitatively.
ISBN: 9783030586096
DOI: 10.1007/978-3-030-58610-2_46
Rights: © 2020 Springer Nature Switzerland AG. This is a post-peer-review, pre-copyedit version of a conference paper published in European Conference on Computer Vision (ECCV). The final authenticated version is available online at:
Fulltext Permission: embargo_20211014
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
  Until 2021-10-14
1.1 MBAdobe PDFUnder embargo until Oct 14, 2021

Page view(s)

Updated on May 13, 2021

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.