Deep Graphics Platinum Pass Full Conference Pass Full Conference One-Day Pass Date: Monday, November 18th Time: 9:00am - 10:45am Venue: Plaza Meeting Room P3 Session Chair: Youyi Zheng, ZJU, China Architecture of Integrated Machine Learning in Low Latency Mobile VR Graphics Pipeline Author(s)/Presenter(s): Haomiao Jiang, Facebook, United States of AmericaRohit Rao Padebettu, Facebook, United States of AmericaKazuki Sakamoto, Facebook, United States of AmericaBehnam Bastani, Facebook, United States of America Abstract: We propose a framework to execute machine learning algorithms in the real time mobile VR graphics pipeline to improve efficiency and image quality. Automatic Generation of Chinese Vector Fonts via Deep Layout Inferring Author(s)/Presenter(s): Yichen Gao, Peking University, ChinaZhouhui Lian, Peking University, ChinaYingmin Tang, Peking University, ChinaJianguo Xiao, Peking University, China Abstract: This paper proposes a data-driven system which integrates the CG-based and deep learning-based methods to generate complete Chinese vector fonts from a small number of designed glyphs. Enhancing Piecewise Planar Scene Modeling from a Single Image via Multi-View Regularization Author(s)/Presenter(s): Weijie Xi, University of Science and Technology of China, ChinaSiyu Hu, University of Science and Technology of China, ChinaZhiwei Xiong, University of Science and Technology of China, ChinaXuejin Chen, University of Science and Technology of China, China Abstract: We propose a method to address the single-image piece-wise planar 3D reconstruction problem. Our key innovation is to enhance a single-view planar reconstruction network by multi-view regularization during training. Unpaired Sketch-to-Line Translation via Synthesis of Sketches Author(s)/Presenter(s): Gayoung Lee, NAVER WEBTOON Corp., NAVER Corporation, South KoreaDohyun Kim, Chung-Ang University, South KoreaYoungjoon Yoo, Clova AI Research, NAVER Corp., South KoreaDongyoon Han, Clova AI Research, NAVER Corp., South KoreaJung-Woo Ha, Clova AI Research, NAVER Corp., South KoreaJaehyuk Chang, NAVER WEBTOON Corp., South Korea Abstract: In this paper, we propose a training scheme that requires only unpaired sketch and line images for learning sketch simplification using both rule-based algorithm and deep learning approach.
