在人工智能内容生成技术取得飞速进展的今天，我们如何理解人工智能算法与内容创作者之间的关系？传统的草图绘画是否还蕴含着有待进一步理解与建模的创造力？如何设计更好支持创作的智能算法与工具？围绕这一主题，拉斯维加斯手机娱乐网站 （CSIG）将于2023年4月27日（周四）08:00-10:30举办CSIG图像图形技术国际在线研讨会第9期（Sketching & Creativity Support Tools）。会议邀请了来自中美的3位国际知名学者来介绍草图与创意支持工具领域的最新研究成果，从视觉感知、创作过程、生成技术三个方面展开讨论，并围绕该领域当下挑战及未来趋势进行展望。期待学术与工业界同行的积极参与！

主办单位：拉斯维加斯手机娱乐网站 （CSIG）

承办单位：CSIG国际合作与交流工作委员会

会议时间：2023年4月27日（周四）08:00-10:30

腾讯会议：182-324-517

会议直播：https://meeting.tencent.com/l/PTatQESfNEHf

长按以下二维码进入

会议日程

讲者简介

Aaron Hertzmann

Adobe Research

Personal Profile：Aaron Hertzmann is a Principal Scientist at Adobe, and Affiliate Faculty at University of Washington. He received a BA in computer science and art/art history from Rice University in 1996, and a PhD in computer science from New York University in 2001. He was a Professor at University of Toronto for 10 years, and has also worked at Pixar Animation Studios and Microsoft Research. He has published over 100 papers in computer graphics, computer vision, machine learning, robotics, human-computer interaction, and art. He is an ACM Fellow and an IEEE Fellow.

Talk title: Why Does Line Drawing Work?

Abstract: How is that line drawings are very different from our natural world, yet they can be understood by people who have never seen pictures before? I argue that this question can be resolved using the idea of Abstracted Shading from computer graphics. That is, the human visual system perceives line drawings as if they were approximately-realistic images. Moreover, the techniques of line drawing are chosen to accurately convey shape to a human observer. Along the way, I discuss contour algorithms in computer graphics and how these ideas could lead to new rendering algorithms.

Li-Yi Wei

Adobe Research

Personal Profile：Li-Yi Wei is a research scientist / manager with Adobe Research, and has been a professor with the University of Hong Kong, a researcher with Microsoft Research, and a GPU architect with NVIDIA. He received his PhD degree from Stanford University. He has served as associate editors for ACM ToG, EG CGF, IEEE TVCG, and paper committee members for SIGGRAPH, SIGGRAPH Asia, and EG. His main recent research focus is on interactive content creation, in particular sketch-based authoring and motion graphics effects.

Talk title: Sketch as a Creative Process for Content Creation

Abstract: People often think that content creation is a linear process, from idea to execution to outcome. However, in reality, it is often an iterative process, in which creators start with rough ideas followed by gradual experimentation and refinement. For such iterative processes, sketching has been found to be a natural way to create, iterate, communicate, and explore ideas. In this talk, we will examine the role of sketch for creativity support and content creation in graphics and HCI across different content types, workflows, and applications, including existing works and future opportunities.

Hongbo Fu

City University of Hong Kong

Personal Profile：Hongbo Fu is a Professor at the School of Creative Media, City University of Hong Kong. He received a PhD degree in computer science from HKUST in 2007 and a BS degree in information sciences from Peking University in 2002. His primary research interests fall in computer graphics, HCI, and computer vision. His research has led to over 100 scientific publications, including 60+ papers in the best graphics/vision journals (ACM TOG, IEEE TVCG, IEEE PAMI, IMWUT) and 20+ papers in the best vision/HCI conferences (CVPR, ICCV, ECCV, CHI, UIST).

Talk title: Sketching Photo-realistic Human Faces

Abstract: Generative AI, e.g., based on ChatGPT and Midjourney, recently has taken a big step and allows the easy generation of unique and high-quality images from short text descriptions. Text prompts are good at describing desired content in a high-level way. However, detailed specification of geometry, structure, and/or appearance via pure text is not easy. On the other hand, sketching is commonly used to quickly depict desired shape information. In this talk, I will introduce a series of sketch-based interfaces developed by my group and collaborators towards photo-realistic human face generation and editing.

主持人简介

王泽宇

香港科技大学（广州）

Personal Profile：Zeyu Wang is an Assistant Professor of Computational Media and Arts (CMA) in the Information Hub at the Hong Kong University of Science and Technology (Guangzhou) and an Affiliate Assistant Professor of Computer Science and Engineering at HKUST. He received a PhD from Yale University and a BS from Peking University. He has published 20 papers in international journals and conferences on Computer Graphics and HCI, including ACM TOG and CHI. His research has been recognized by an Adobe Research Fellowship, a Best Paper Award, and a Best Demo Honorable Mention Award.