讲座:End-to-End Projector Compensation端到端投影仪补偿
演讲者:Haibin Ling, SUNY Empire Innovation Professor,Department of Computer Science, Stony Brook University
Haibin Ling received the B.S. and M.S. degrees from Peking University in 1997 and 2000, respectively, and the Ph.D. degree from the University of Maryland, College Park, in 2006. From 2000 to 2001, he was an assistant researcher at Microsoft Research Asia. From 2006 to 2007, he worked as a postdoctoral scientist at the University of California Los Angeles. From 2008 to 2019, he worked as a faculty member of Temple University. In 2019, he joined the Department of Computer Science of Stony Brook University where he is currently a SUNY Empire Innovation Professor. His research interests include computer vision, augmented reality, medical image analysis, and human computer interaction. He received the NSF CAREER Award in 2014. He serves as Associate Editors for several journals including IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), Pattern Recognition (PR), and Computer Vision and Image Understanding (CVIU). He has served or will serve as Area Chairs for CVPR 2014, 2016, 2019 and 2020.
Projector compensation aims to modify a projector input image such that it can compensate for geometric correction and photometric disturbance of the projection surface. The photometric process in a projector-camera (ProCam) system involves many complicated factors, making it very difficult for traditional solutions. In this work, we propose end-to-end solutions by that implicitly address real-world challenges. First, we formulate the compensation problem as an end-to-end learning problem and propose a convolutional neural network, named CompenNet, to implicitly learn the complex compensation function. CompenNet consists of a UNet-like backbone network and an autoencoder subnet. Then, we further extend CompenNet by integrating a geometric correction subset for geometric compensation, while remaining end-to-end trainable. For evaluation, we construct the first setup-independent full compensation benchmark to facilitate the study on this topic. In our thorough experiments, our method shows clear advantages over previous arts with promising compensation quality and meanwhile being practically convenient.