Neural substrates dedicated to vision is said to occupy about 40 percent of the cerebral cortex. Realizing computer vision as a truly intelligent perceptual modality is fundamental for artificial intelligence, and would also inform our understanding of human visual intelligence. Towards computational visual intelligence, our research is focused on establishing the theoretical foundations and efficient implementations of computational methods for better understanding people, objects and scenes from their appearance in images and video, as well as the development of novel computational imaging systems that can see beyond what we see.
Our lab started in April 2018 with PI Nishino’s return to Japan from the US. Our current research centers around human modeling and behavior analysis; appearance modeling, inverse rendering, and material recognition; and physics-based vision and computational photography. Our research finds applications in AR/VR, graphics, HCI, and robotics, and our current focus is autonomous driving, driving assistance, elderly care, and assisted living. Please check out research and publication for samples of research conducted in our lab. You can find many of our code and data, too. We are constantly looking for qualified students and postdocs. If you are interested in joining our lab, please contact us.