The Magic of Images Platinum Pass Full Conference Pass Full Conference One-Day Pass Date: Sunday, November 17th Time: 2:15pm - 4:00pm Venue: Plaza Meeting Room P3 Session Chair: Diego Gutierrez, Universidad de Zaragoza, International Imaging Industry Association (I3A) A Decomposition Method of Object Transfiguration Author(s)/Presenter(s): Seung Joon Lee, Sogang University, South KoreaKeon-Woo Kang, Sogang University, South KoreaSiyeong Lee, NAVER LABS, South KoreaSuk-Ju Kang, Sogang University, South Korea Abstract: The method that decomposes an object transfiguration task into two subtasks is proposed:object removal and object synthesis. We formulate each task distinguishing a background and an object using instance information. ChinaStyle: A Mask-Aware Generative Adversarial Network for Chinese Traditional Image Translation Author(s)/Presenter(s): Yuan Wang, Institute of Information Engineering, Chinese Academy Of Sciences, ChinaWeibo Zhang, Institute of Information Engineering, Chinese Academy Of Sciences; School of Cyber Security, University of Chinese Academy of Sciences, ChinaPeng Chen, Institute of Information Engineering, Chinese Academy Of Sciences; School of Cyber Security, University of Chinese Academy of Sciences, China Abstract: This paper introduced MA-GAN to generate Chinese traditional paintings from portrait photos with our training dataset. The experiment shows it is more effective than existing methods both quantitatively and qualitatively. Structure-Aware Image Expansion with Global Attention Author(s)/Presenter(s): Dewen Guo, Peking University, ChinaJie Feng, Peking University, ChinaBingfeng Zhou, Peking University, China Abstract: We propose a learning-based method combining structure-aware and visual attention strategies to for image expansion. We apply our method on a human face dataset, which containing semantic and structural details. The Power of Box Filters: Real-time Approximation to Large Convolution Kernel by Box-filtered Image Pyramid Author(s)/Presenter(s): Tianchen Xu, Advanced Micro Devices, Inc. (AMD), ChinaXiaohua Ren, Tencent Youtu X-Lab, ChinaEnhua Wu, State Key Lab of CS, Institute of Software, Chinese Academy of Sciences & Univ. of CAS; University of Macau, China Abstract: This paper presents a novel solution for approximations to some large convolution kernels by leveraging a weighted box-filtered image pyramid set. Our algorithm is kernel-size independent, and fast on GPU.