GAMES Webinar 2021 – 174期(几何处理专题) | Wenzheng Chen (University of Toronto)
【GAMES Webinar 2021-174期】(几何处理专题)
报告嘉宾：Wenzheng Chen (University of Toronto)
报告题目：Differentiable Imaging System
3D perception is one of the fundamental problems in computer vision, with numerous applications ranging from AR/VR to industrial automation. Various 3D imaging systems, together with AI based methods, are proposed to address this problem. However, existing techniques are always restricted in different aspects. For example, AI based methods require 3D training data, which is very expensive to acquire. Stereo matching, relying on correspondence, would easily fail on a white wall. Active 3D imaging systems (i.e. Structured Light or Time of Flight) infer depth by actively sending and receiving light signals, which would be trapped in complex materials (light propagation path is hard to compute) or low SNR (receiving too weak signals in dark environment).
In this talk, I will introduce several projects which try to overcome these limitations. The key idea is to differentiate imaging systems and incorporate them with deep learning. Turning imaging systems to be differentiable is a prerequisite to put them in SGD optimization, while the learning systems, built on top of imaging systems, could inherently utilize the specific geometric or optical rules inside the imaging systems, resulting in much better performance than traditional black box neural networks. We demonstrate that such a combination brings huge benefits.
Wenzheng Chen is a fourthth-year Ph.D. student at University of Toronto, supervised by Prof. Sanja Fidler and Prof. Kyros Kutulakos. He is also a research scientist at NVIDIA. His research mainly focuses on the intersection of computational photography and machine learning, with a special interest in estimating 3D properties from various imaging systems. His long term research goal is to explore all kinds of optical and physical rules in the imaging systems and embed them in deep learning to boost 3D perception. He received his MS and BS in Shandong University. For more information, please visit http://www.cs.toronto.edu/~wenzheng/.
徐凯，国防科技大学教授。2011年于国防科大计算机学院获得博士学位。普林斯顿大学访问学者。西蒙弗雷泽大学客座教授。研究方向为三维视觉及其机器人应用、数据驱动的三维几何处理与建模等。发表ACM SIGGRAPH/Transactions on Graphics论文20余篇。共发表CCF A类论文40余篇。担任图形学顶级国际期刊ACM Transactions on Graphics，以及重要期刊Computer Graphics Forum、Computers and Graphics和The Visual Computer等的编委。担任CAD/Graphics 2017、ISVC 2018等国际会议的论文共同主席，以及SIGGRAPH、Eurographics等会议的程序委员。担任中国图象图形学会三维视觉专委会副主任，中国工业与应用数学学会几何设计与计算专委会秘书长。曾获湖南省自然科学一等奖、中国计算机学会自然科学一等奖、军队科技进步二等奖等。曾获国家优秀青年基金和湖南省杰出青年基金资助。
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；