GAMES Webinar 2026 – 393期(面向可视化与视觉计算的结构保持型数据表示) | 叶铧远（华东师范大学），李宇诗（西交利物浦大学）
GAMES Webinar 2026 – 393期(面向可视化与视觉计算的结构保持型数据表示)
报告嘉宾： 叶铧远（华东师范大学）
报告时间：2026年01月22号 晚上8:00-8:30（北京时间）
报告题目：可逆可视化：如何避免可视化传播过程中的信息丢失
报告摘要：
可视化图表在传播时常以静态图像呈现，导致其原有的交互属性与底层数据丢失。因此，如何在传播过程中有效保留图表的原始功能成为重要挑战。可逆可视化致力于通过逆向工程，从图表图像中恢复其结构与数据。早期研究主要通过目标检测方法分析图表样式与视觉编码以还原信息。然而，随着可视化样式日益复杂，此类方法难以保证还原的准确性和可靠性。近年来，图像隐写技术，即以视觉不可见的方式在图像中嵌入信息，为该问题提供了新的解决思路。本报告探讨如何利用图像隐写技术实现图表传播过程中的可逆可视化。首先，针对大规模数据可视化图表，我们提出了一种高效的数据-图像编码方案，以实现高质量信息嵌入。此外，针对传播中可能发生的编辑、篡改等干扰，我们还提出一种鲁棒的可逆可视化框架，既能确保嵌入数据被稳定恢复，也能检测可视化在传播过程中是否遭篡改。该方法使用户能够在图表中灵活嵌入多种信息，可用于版权保护和防篡改验证等应用，从而避免因图像被修改而传递误导性信息。
讲者简介：
Huayuan Ye is currently pursuing his M.S. degree at the School of Computer Science and Technology, East China Normal University, while also serving as a Research Assistant at The Hong Kong University of Science and Technology. His research focuses on the intersection of visualization and artificial intelligence, with primary directions in visualization reverse engineering, large-scale spatiotemporal data analysis, and scientific visualization. His work has been published in international conferences and journals such as IEEE VIS, ACM CHI, AAAI and CVPR, including three CCF-A tier first-author papers. He also holds two authorized national invention patents.
Personal website: huayuan.info
报告嘉宾：李宇诗（西交利物浦大学）
报告时间：2026年01月22号 晚上08:30-09:50（北京时间）
报告题目：
图学习与3D点云结构生成
报告摘要：
如何生成高质量、结构合理的三维点云，是计算机视觉与图形学领域的核心挑战。近年来，以生成对抗网络（GAN）为框架，融合图表示学习的模型在这一领域取得了突破性进展。针对“图结构学习”框架下的点云学习，我们提出了一系列代表性工作。首先，是分层感知机制的引入，它通过构建多尺度图结构使模型能同时捕获全局形状与局部细节。其次，是显式图拓扑引导的范式，它将生成过程重新定义为图构建问题，利用图卷积编码强几何先验，从而显著提升了对复杂、非均匀结构（如机械零件、生物结构）的生成能力。最后，我们聚焦于最新的动态结构优化方向，这一方法通过可学习的、迭代的图构建过程，实现了对点云局部与全局关系自适应建模。
讲者简介：
Yushi Li received the Ph.D from The Hong Kong Polytechnic University, in 2021. He is currently an assistant professor at the Department of Intelligent Science, Xi’an Jiaotong-Liverpool University. His main research interests include computer vision and computer graphics. He has published over 40 papers on IEEE TIP, TVCG, TNNLS, TCE, ESWA, CVPR, WACV and others. He serves as the reviewer for IEEE TVCG, TNNLS, TCSVT, KBS, Neurocomputing, Computers&Graphics, CAD/CG, CVPR, Eurographics, CHI, WWW, ECAI, ICME, UIC, CSCWD, ChinaVis and others. He also served as the PC member or Co-Chair of serveral international conferences such as WWW 2025, ECAI 2025, WWW 2024 (Industry track), ECAI 2024, and ICVR 2023 (special session).
主持人简介：
Chengtao Ji received his M.S. and Doctoral degree from Sichuan University and Groningen University in 2014 and 2018, respectively. He is currently an assistant professor in Xi’an Jiaotong-Liverpool University, China. His research interests include data mining, complex network analysis, and visual analytics.
Yunzhe Wang received her M.S. and PhD in Computer Science from The University of Hong Kong and The Hong Kong Polytechnic University in 2014 and 2020, respectively. She is currently an associate professor in Suzhou University of Science and Technology, China. Her research interests include data science, social networks, and visual analysis. She has published paper on top conferences and journals including Computer Graphics Forum and ACM Transactions on Knowledge Discovery from Data and so on. She received ICCI*CC Best Paper Award in 2015, SIGGRAPH Asia Sym. Vis. Best Paper Award in 2017 and Jiangsu Innovation and Entrepreneurship Ph.D. from World Prestigious Universities Award in 2021.
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：https://live.bilibili.com/h5/24617282
