The 2022 CHCCS/SCDHM Achievement Award of the Canadian Human-Computer Communications Society is presented to Dr. Hao (Richard) Zhang for his numerous high-impact contributions to computer graphics. His research addresses fundamental problems in geometric modeling, shape analysis, geometric deep learning, and computational design and fabrication. Richard is a Distinguished Professor at Simon Fraser University and an Amazon Scholar. He directs the GrUVi (Graphics U Vision) lab at SFU. He has also been a visiting professor at Stanford University (2016-17), Shenzhen University (2017-now), and the Beijing Film Academy (2018-20).
Richard obtained his Ph.D. from the University of Toronto, under Eugene Fiume, and MMath and BMath degrees from the University of Waterloo, all in computer science. To date, he has published more than 160 papers on various topics in visual computing, including 60+ articles in SIGGRAPH, SIGGRAPH Asia, and ACM Trans. on Graphics, the most prestigious venue in computer graphics. Methods from three of his papers on geometry processing have been adopted by CGAL, the open-source Computational Geometry Algorithms Library. According to Google Scholar, Richard has a total citation count of 13K+ and an h-index of 55. Richard is an associate editor-in-chief for IEEE Computer Graphics & Applications (CG&A), a past editor-in-chief for Computer Graphics Forum, and an associate editor for ACM Trans. on Graphics and IEEE TVCG. He has served on the program committees of all major computer graphics conferences and is SIGGRAPH Asia 2014 course chair, a paper co-chair for SGP 2013, GI 2015, and CGI 2018, and a program chair for International Geometry Summit 2019.
In the early stages of Richard’s career, he made seminal contributions to spectral geometry processing. His mesh segmentation paper in 2004 was the first to bring the spectral approach to shape analysis in graphics. He also wrote the first survey on the topic. Spectral methods have since become a standard tool in visual computing. In 2009-10, Richard published several foundational papers on using symmetry priors for shape analysis and representation, in particular, symmetry hierarchies. This work laid the groundwork for his SIGGRAPH 2017 paper on GRASS, the first deep generative neural network for 3D shape structures. Also, in his early works, Richard already realized a connection between symmetry and functionality, which led to a series of SIGGRAPH papers (2015-18) on functional analysis of 3D shapes. These works are ground-breaking in graphics and critical to 3D shape understanding, design, and generation for which the ultimate goal is at the functional level.
Richard is best known for his sustained and impactful contributions to learning-based analysis and synthesis of visual data, especially 3D shapes and indoor scenes. His ICCV 2017 paper DualGAN, together with CyclaGAN, pioneered the dual learning approach for unsupervised domain translation using a cycle consistency loss. Most recently, at CVPR 2019, he published a paper on learning implicit fields for generative shape modeling. This work, called IM-Net, together with DeepSDF and OccNet, started a mini revolution on neural implicit representations for geometric deep learning. In a very short time, significant advances over implicit models have been achieved, leading to BSP-Net, which won the Best Student Paper Award at CVPR 2020. Other major awards won by Richard include an NSERC DAS (Discovery accelerator Supplement) Award in 2014, a National Science Foundation of China (NSFC) Overseas Outstanding Young Researcher Award in 2015, a Google Faculty Research Award in 2019, a Best Dataset Award from ChinaGraph (2020), as well as Best Paper Awards at SGP 2008 and CAD/Graphics 2017. As of 2022, both Richard’s CVPR and SGP works have been the only award-winning papers at these venues for which all authors had Canadian affiliations at the time of publication: four from SFU and one from Google Brain Toronto, who happens to be a former PhD of Richard’s from SFU.