Vision, Interaction, Graphics, Robotics

The center brings together researchers in the areas of vision, graphics, human-computer interaction, robotics, modeling, and learning. Our goal is to make fundamental impact on the ways in which visual information is captured, manipulated, and experienced.


In recent years, the fields of computer vision and computer graphics have converged to produce new and compelling forms of visual information. This convergence has given rise to a powerful set of techniques, such as image-based scene modeling, image-based rendering, computational video, and visual user interfaces. Our research environment is unique: it exploits the strengths in areas that are core to the convergence, it addresses a diverse set of research problems, and it has a highly collaborative spirit. Our work is motivated by applications in many areas, including digital imaging, television, games, visualization, education, robotics, and wearable computing.


  • Mar 2022: Five papers accepted to CVPR 2022! Congratulations to Chengzhi, Didac, Basile and Purva.
  • Feb 2022: Shuran Song was selected as a 2022 Sloan Research Fellow.
  • Jan 2022: Two papers accepted to ICLR 2022! Congratulations Mia and Chenzhi.
  • Nov 2021: FlingBot won Best System Paper Award at CoRL 2021! Congratulations Huy!
  • Nov 2021: Two papers accepted to CoRL 2021! Congratulations Huy, Bo and Mia.
  • Oct 2021: Didac Suris is awarded the Microsoft PhD Fellowship!
  • May 2021: Three papers accepted to ICCV 2021! Congratulations to Rundi, Chengzhi, Basile and Mia.