Deep Unsupervised Pixelization

• Main Authors: HAN, Chu, WEN, Qiang, HE, Shengfeng, ZHU, Qianshu, TAN, Yinjie, HAN, Guoqiang, WONG, Tien-Tsin
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2018
• Subjects: Adversarial networks; Downscaling methods; Feature representation; Image translation; Pixelization; State-of-the-art methods; Structured images; Unsupervised learning method; Databases and Information Systems; Digital Communications and Networking
• Online Access: https://ink.library.smu.edu.sg/sis_research/8449; https://ink.library.smu.edu.sg/context/sis_research/article/9452/viewcontent/Deep_unsupervised_pixelization.pdf
• Institution: Singapore Management University

In this paper, we present a novel unsupervised learning method for pixelization. Due to the difficulty in creating pixel art, preparing the paired training data for supervised learning is impractical. Instead, we propose an unsupervised learning framework to circumvent such difficulty. We leverage t...