Mesh-Based Freeform Lens Optimization for Light Control
13:30-13:42
吴文明
合肥工业大学
几何增强的矢量平面图生成方法研究
13:42-13:54
刘中远
腾讯
艺术创作的慢思考
13:54-14:06
洪阳
华为
AI渲染技术的业务应用与挑战
14:06-14:18
陈文博
英伟达
GPU与图形技术发展趋势
14:18-14:30
Q&A
14:30-14:45
茶歇
14:45-16:10
Session 2,主持人:李新
14:45-15:10
汪子琦
香港科技大学
Computational Assemblies: Bridging the Gap from Concept to Production
15:10-15:22
吴梦
南京理工大学
复杂几何的设计与仿真
15:22-15:34
康红梅
苏州大学
三角剖分上的等几何分析
15:34-15:46
郑野
上海柏楚
图形智造中的几何算法
15:46-15:58
陆炎
先临三维
高精度三维扫描的行业应用
15:58-16:10
Q&A
16:10-16:25
茶歇
16:25-18:02
Session 3,主持人:张举勇
16:25-16:50
陈旭
Google
三维数字人的表达,重建与生成
16:50-17:02
王春雪
杭州电子科技大学
数字文化遗产智能化建设的探索与实践
17:02-17:14
刘雨萌
香港大学
人手到机械手:基于单视图的手物重建和五指机械手的抓取生成
17:14-17:26
樊鲁斌
阿里云
Relaxing Constraints of NeRF and 3DGS for Practical Applications
17:26-17:38
李哲
华为
基于3D Gaussian Splatting的可驱动数字人建模
17:38-17:50
李威
网易
图形学和AI技术在游戏角色制作中的应用
17:50-18:02
Q&A
18:02-18:10
总结及闭幕
讲者与报告
题目: Mesh-Based Freeform Lens Optimization for Light Control
讲者: 邓柏林, Cardiff University
摘要: Designing a freeform surface that reflects or refracts light to achieve a target distribution is a challenging inverse problem. In this talk, I will present two recent works on optimizing freeform lenses represented as triangle meshes to create desired caustic patterns. The first work introduces a differentiable rendering model that calculates caustics from a mesh surface without the need for sampling. This model enables direct optimization based on the difference between the target and resulting caustic images, leading to single-sided freeform lens designs with caustics closely matching the target. In the second work, we propose a technique that simultaneously optimizes both sides of a freeform lens, using a bijective correspondence between the two sides to control light refraction paths. Our preliminary results are promising, suggesting new possibilities for freeform optics design.
个人简介: Bailin Deng is a Senior Lecturer in the School of Computer Science and Informatics at Cardiff University, where he leads the Geometric Computing and Graphics Research Group. He holds a BEng in Computer Software and an MSc in Computer Science from Tsinghua University, as well as a PhD in Technical Mathematics from the Vienna University of Technology. Before joining Cardiff University in 2017, he worked as a postdoctoral researcher at the Computer Graphics and Geometry Laboratory at EPFL, and as a Lecturer in the School of Computer Science at the University of Hull. His research focuses on 3D geometry processing and the development of numerical algorithms, with applications in computational design, geometric modeling, and computer animation.
题目: Computational Assemblies: Bridging the Gap from Concept to Production
讲者: 汪子琦, 香港科技大学
摘要: Assemblies are ubiquitous in our daily lives, with applications ranging from small toys to large buildings. By combining parts of simpler shapes, assemblies enable the creation of complex structures, an approach extensively adopted in construction and manufacturing industries.
Making assembly was once a labor-intensive process. Advancements in automation have led to the increased use of robots to accomplish assembly tasks. Still, designing and fabricating complex assemblies poses a significant intellectual challenge. Current design and fabrication workflows require designers to specify numerous low-level details, which limits creativity and efficiency. Therefore, to address the challenges in current assembly design and fabrication, my research focuses on developing a new end-to-end concept-to-production workflow called computational assemblies. In this talk, I'll be excited to showcase how my new computational algorithms are opening doors to:
1. Computational design of infinitely reusable structural systems.
2. Computational fabrication of complex assemblies using augmented reality (AR) and robotics.
个人简介: Ziqi Wang is an Assistant Professor at the Division of Integrative Systems and Design (ISD) at the Hong Kong University of Science and Technology (HKUST). Before joining HKUST, he worked as a postdoctoral researcher at the Creative Computation Lab and Sycamore at École Polytechnique Fédérale de Lausanne (EPFL) in 2024, under the supervision of Prof. Stefana Parascho and Prof. Maryam Kamgarpour. Prior to that, he was a postdoctoral researcher at the Computational Robotics Lab at ETH Zurich, advised by Prof. Stelian Coros. He obtained his Ph.D. in 2021 from the Geometric Computing Laboratory at EPFL, where he was advised by Prof. Mark Pauly. He completed his bachelor's degree in Mathematics in 2017 at the University of Science and Technology of China (USTC).
Ziqi is interested in interdisciplinary projects that connect architecture, robotics, and computer graphics. His current research focuses on the computational design, analysis, and fabrication of complex assemblies, with applications ranging from toys and furniture to buildings. The goal is to create a seamless end-to-end workflow that enables users to design and fabricate personalized items using artificial intelligence and robotics. He has years of experience collaborating with researchers from various disciplines, including robotics, architecture, and civil and mechanical engineering. He has applied his research to constructing several large-scale architectural demonstrators. He has published 7 papers in the top computer graphics journal, ACM Transactions on Graphics (TOG), and received a Best Paper Honorable Mention Award at SIGGRAPH 2022.