Computational photography aims at improving photographs through computation. Many algorithms have been developed for making photographs better by combating with the imperfection of cameras, photographers, and scenes. Recently, deep learning has been shown effective for many computational photography problems such as super-resolution, image completion, frame interpolation and many others. In this talk, I will review these deep learning methods for computational photography.
Yung-Yu Chuang is a professor in the Department of Computer Science and Information Engineering at National Taiwan University. He received his B.S. and M.S. from National Taiwan University in 1993 and 1995 respectively, Ph.D. from the University of Washington in 2004, all in Computer Science. His research interests include computer graphics and computer vision, more specifically computation photography, stereoscopic media processing and rendering.