GAMES Webinar 2018 -73期(Siggraph Asia 2018论文报告)| 王杨抟风(伦敦大学学院),李昌健(香港大学)
【GAMES Webinar 2018-73期(Siggraph Asia 2018论文报告)】
报告嘉宾1:王杨抟风,伦敦大学学院
报告时间:2018年11月15日 晚8:00-8:45(北京时间)
主持人:徐昆,清华大学(个人主页:https://cg.cs.tsinghua.edu.cn/people/~kun/)
报告题目:Learning a Shared Shape Space for Multimodal Garment Design
报告摘要:
Designing real and virtual garments is becoming extremely demanding with rapidly changing fashion trends and increasing need for synthesizing realistically dressed digital humans for various applications. This necessitates creating simple and effective workflows to facilitate authoring sewing patterns customized to garment and target body shapes to achieve desired looks. Traditional workflow involves a trial-and-error procedure wherein a mannequin is draped to judge the resultant folds and the sewing pattern iteratively adjusted until the desired look is achieved. This requires time and experience. Instead, we present a data-driven approach wherein the user directly indicates desired fold patterns simply by sketching while our system estimates corresponding garment and body shape parameters at interactive rates. The recovered parameters can then be further edited and the updated draped garment previewed. Technically, we achieve this via a novel shared shape space that allows the user to seamlessly specify desired characteristics across multimodal input without requiring to run garment simulation at design time. We evaluate our approach qualitatively via a user study and quantitatively against test datasets, and demonstrate how our system can generate a rich quality of on-body garments targeted for a range of body shapes while achieving desired fold characteristics. Code and data are available at our project webpage.
讲者简介:
Tuanfeng currently is a PhD student in Computer Science at University College London. Since 2014, he is a member of Smart Geometry Processing Group, advised by Niloy J. Mitra. Before that, he studied in University of Science and Technology of China under supervision of Prof. Ligang Liu.
讲者个人主页:http://geometry.cs.ucl.ac.uk/tuanfeng/
报告嘉宾2:李昌健,香港大学
报告时间:2018年11月15日 晚8:45-9:30(北京时间)
主持人:徐昆,清华大学(个人主页:https://cg.cs.tsinghua.edu.cn/people/~kun/)
报告题目:Robust Flow-Guided Neural Prediction for Sketch-Based Freeform Surface Modeling
报告摘要:
二维草图是一种描述三维形状直观,形象的方式,很多研究工作基于草图来造型三维物体,但是他们往往依赖于繁复的用户标记或者限定于某一类或几类物体。我们提出了一种新的方法,以卷积神经网络为核心,基于用户少量的,形象的二维草图来造型类别不限的自由曲面片,从而造型三维物体。给定二维草图,我们使用神经网络来预测表达曲面的深度图和法向图。同时为了减少二维草图到三维曲面的二义性,我们引入了一个子网络来预测稠密的投影曲率方向场,而且除了产生深度和法向外,我们还会产生一张置信图,这里曲率方向场会帮助我们产生更规则的曲面形状,而置信图采用了非监督的方式训练,一方面可以来评估结果的二义性大小,另一方面还使得数据拟合更加鲁棒。为了进一步减小二义性和编辑形状,用户可以提供稀疏的深度值或者关于曲率的一些提示(曲率值符号和大小)作为神经网络的额外输入,使得结果更符合预期。用户可以在选定的任意视图下造型曲面,多个视图下的曲面最终融合成完整的三维形状。我们通过造型一系列复杂程度各异的三维物体和普通用户的体验评估,证明了我们的方法的有效性。
讲者简介:
李昌健,香港大学计算机系博士生,师从王文平教授。2014年本科毕业于山东大学,2016-2018年期间,多次在微软亚洲研究院实习,合作并发表了基于草图快速建模的工作。研究兴趣主要包括基于草图的交互式三维造型,深度学习,交互式材料建模等。
讲者个人主页:https://enigma-li.github.io/
GAMES主页的“使用教程”中有 “如何观看GAMES Webinar直播?”及“如何加入GAMES微信群?”的信息;
GAMES主页的“资源分享”有往届的直播讲座的视频及PPT等。
观看直播的链接:http://webinar.games-cn.org