Cascade EF-GAN : progressive facial expression editing with local focuses
Recent advances in Generative Adversarial Nets (GANs) have shown remarkable improvements for facial expression editing. However, current methods are still prone to generate artifacts and blurs around expression-intensive regions, and often introduce undesired overlapping artifacts while handling lar...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/146680 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-146680 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1466802021-03-04T08:40:00Z Cascade EF-GAN : progressive facial expression editing with local focuses Wu, Rongliang Zhang, Gongjie Lu, Shijian Chen, Tao School of Computer Science and Engineering 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Data Science and Artificial Intelligence Research Centre Engineering Computer Vision Generative Adversarial Nets (GANs) Recent advances in Generative Adversarial Nets (GANs) have shown remarkable improvements for facial expression editing. However, current methods are still prone to generate artifacts and blurs around expression-intensive regions, and often introduce undesired overlapping artifacts while handling large-gap expression transformations such as transformation from furious to laughing. To address these limitations, we propose Cascade Expression Focal GAN (Cascade EF-GAN), a novel network that performs progressive facial expression editing with local expression focuses. The introduction of the local focus enables the Cascade EF-GAN to better preserve identity-related features and details around eyes, noses and mouths, which further helps reduce artifacts and blurs within the generated facial images. In addition, an innovative cascade transformation strategy is designed by dividing a large facial expression transformation into multiple small ones in cascade, which helps suppress overlapping artifacts and produce more realistic editing while dealing with large-gap expression transformations. Extensive experiments over two publicly available facial expression datasets show that our proposed Cascade EF-GAN achieves superior performance for facial expression editing. Nanyang Technological University Accepted version This work is supported by Data Science & Artificial Intelligence Research Centre, NTU Singapore. 2021-03-04T08:40:00Z 2021-03-04T08:40:00Z 2020 Conference Paper Wu, R., Zhang, G., Lu, S., & Chen, T. (2020). Cascade EF-GAN : progressive facial expression editing with local focuses. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1, 5020-5029. doi:10.1109/CVPR42600.2020.00507 978-1-7281-7168-5 2575-7075 https://hdl.handle.net/10356/146680 10.1109/CVPR42600.2020.00507 2-s2.0-85093095701 1 5020 5029 en #001531-00001 © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work is available at: https://doi.org/10.1109/CVPR42600.2020.00507 application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering Computer Vision Generative Adversarial Nets (GANs) |
spellingShingle |
Engineering Computer Vision Generative Adversarial Nets (GANs) Wu, Rongliang Zhang, Gongjie Lu, Shijian Chen, Tao Cascade EF-GAN : progressive facial expression editing with local focuses |
description |
Recent advances in Generative Adversarial Nets (GANs) have shown remarkable improvements for facial expression editing. However, current methods are still prone to generate artifacts and blurs around expression-intensive regions, and often introduce undesired overlapping artifacts while handling large-gap expression transformations such as transformation from furious to laughing. To address these limitations, we propose Cascade Expression Focal GAN (Cascade EF-GAN), a novel network that performs progressive facial expression editing with local expression focuses. The introduction of the local focus enables the Cascade EF-GAN to better preserve identity-related features and details around eyes, noses and mouths, which further helps reduce artifacts and blurs within the generated facial images. In addition, an innovative cascade transformation strategy is designed by dividing a large facial expression transformation into multiple small ones in cascade, which helps suppress overlapping artifacts and produce more realistic editing while dealing with large-gap expression transformations. Extensive experiments over two publicly available facial expression datasets show that our proposed Cascade EF-GAN achieves superior performance for facial expression editing. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Wu, Rongliang Zhang, Gongjie Lu, Shijian Chen, Tao |
format |
Conference or Workshop Item |
author |
Wu, Rongliang Zhang, Gongjie Lu, Shijian Chen, Tao |
author_sort |
Wu, Rongliang |
title |
Cascade EF-GAN : progressive facial expression editing with local focuses |
title_short |
Cascade EF-GAN : progressive facial expression editing with local focuses |
title_full |
Cascade EF-GAN : progressive facial expression editing with local focuses |
title_fullStr |
Cascade EF-GAN : progressive facial expression editing with local focuses |
title_full_unstemmed |
Cascade EF-GAN : progressive facial expression editing with local focuses |
title_sort |
cascade ef-gan : progressive facial expression editing with local focuses |
publishDate |
2021 |
url |
https://hdl.handle.net/10356/146680 |
_version_ |
1696984346921009152 |