TY - JOUR
T1 - Template-Free Try-On Image Synthesis via Semantic-Guided Optimization
AU - Chou, Chien Lung
AU - Chen, Chieh Yun
AU - Hsieh, Chia Wei
AU - Shuai, Hong-Han
AU - Liu, Jiaying
AU - Cheng, Wen-Huang
N1 - Publisher Copyright:
IEEE
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2021/2/26
Y1 - 2021/2/26
N2 - The virtual try-on task is so attractive that it has drawn considerable attention in the field of computer vision. However, presenting the 3-D physical characteristic (e.g., pleat and shadow) based on a 2-D image is very challenging. Although there have been several previous studies on 2-D-based virtual try-on work, most: 1) required user-specified target poses that are not user-friendly and may not be the best for the target clothing and 2) failed to address some problematic cases, including facial details, clothing wrinkles, and body occlusions. To address these two challenges, in this article, we propose an innovative template-free try-on image synthesis (TF-TIS) network. The TF-TIS first synthesizes the target pose according to the user-specified in-shop clothing. Afterward, given an in-shop clothing image, a user image, and a synthesized pose, we propose a novel model for synthesizing a human try-on image with the target clothing in the best fitting pose. The qualitative and quantitative experiments both indicate that the proposed TF-TIS outperforms the state-of-the-art methods, especially for difficult cases.
AB - The virtual try-on task is so attractive that it has drawn considerable attention in the field of computer vision. However, presenting the 3-D physical characteristic (e.g., pleat and shadow) based on a 2-D image is very challenging. Although there have been several previous studies on 2-D-based virtual try-on work, most: 1) required user-specified target poses that are not user-friendly and may not be the best for the target clothing and 2) failed to address some problematic cases, including facial details, clothing wrinkles, and body occlusions. To address these two challenges, in this article, we propose an innovative template-free try-on image synthesis (TF-TIS) network. The TF-TIS first synthesizes the target pose according to the user-specified in-shop clothing. Afterward, given an in-shop clothing image, a user image, and a synthesized pose, we propose a novel model for synthesizing a human try-on image with the target clothing in the best fitting pose. The qualitative and quantitative experiments both indicate that the proposed TF-TIS outperforms the state-of-the-art methods, especially for difficult cases.
KW - Cross-modal learning
KW - image synthesis
KW - pose transfer
KW - semantic-guided learning
KW - virtual try-on
UR - http://www.scopus.com/inward/record.url?scp=85101822270&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2021.3058379
DO - 10.1109/TNNLS.2021.3058379
M3 - Article
C2 - 33635797
AN - SCOPUS:85101822270
SN - 2162-237X
VL - 33
SP - 4584
EP - 4597
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 9
ER -