Paper
22 October 2021 A repair model to improve arm problem in semantic segmentation generation
Yining Gao, Pengyuan Zhang, Ming Zheng, Xiaomeng Guo, Pengjian Yang
Author Affiliations +
Proceedings Volume 11928, International Conference on Image Processing and Intelligent Control (IPIC 2021); 119280Y (2021) https://doi.org/10.1117/12.2611381
Event: International Conference on Image Processing and Intelligent Control (IPIC 2021), 2021, Lanzhou, China
Abstract
Image visual try-on aims to transfer the target clothing image to the reference person, and it has become a hot topic in recent years. Current techniques usually focus on preserving the character of clothing images when warping it to arbitrary human pose. However, it is still a challenge to produce realistic try-on images when the reference person has a complicated pose. We propose a novel repair model to solve this problem. We train the network by simulating arm breaks and improper occlusion, so that it can be automatically repaired. Compared to the newest advanced techniques, we improve upon the inaccuracy in the predicted semantic segmentation, proposed a new generator model to obtain more detail from images.
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yining Gao, Pengyuan Zhang, Ming Zheng, Xiaomeng Guo, and Pengjian Yang "A repair model to improve arm problem in semantic segmentation generation", Proc. SPIE 11928, International Conference on Image Processing and Intelligent Control (IPIC 2021), 119280Y (22 October 2021); https://doi.org/10.1117/12.2611381
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Image processing

Composites

Visualization

Data modeling

Image fusion

Image quality

RELATED CONTENT


Back to Top