Traditional visual computing has primarily focused on modeling the transport of RGB light intensity in image formation, enabling perception and reconstruction tasks at a human-level understanding. In this talk, I will introduce our recent work on computational illumination—active imaging systems that exploit richer properties of light, including spectrum, polarization, and phase. These systems open up new possibilities for high-dimensional visual computing, such as 360° 3D imaging, full-space holography, hyperspectral 3D reconstruction, real-time polarimetric imaging, and illumination-robust vision in complex scenes.

Seung-Hwan Baek is an Assistant Professor in the Department of Computer Science and Engineering at POSTECH and is jointly affiliated with the Graduate School of AI. He leads the POSTECH Computational Imaging Group and serves as co-director of the POSTECH Computer Graphics Lab. Prof. Baek received his Ph.D. in Computer Science from KAIST and was a postdoctoral researcher at Princeton University. His research lies at the intersection of computer graphics, computer vision, AI, and optics, with a focus on capturing, modeling, and interpreting high-dimensional visual data shaped by the complex interplay of light, material, and geometry. His work has broad applications in mobile imaging, robotics, autonomous systems, AR/VR displays, and scientific instrumentation. He has been recognized with several honors, including the Frontiers of Science Award from the International Congress of Basic Science, the Outstanding Ph.D. Thesis Award in IT from the Korean Academy of Science and Technology, the SIGGRAPH Asia Doctoral Consortium selection, the Microsoft Research Asia Ph.D. Fellowship, and best paper/demo awards at ACCV.