Seminar | June 23 | 12-1 p.m. | Zoom
Forrest Huang
Electrical Engineering and Computer Sciences (EECS)
Sketching and prototyping are central to creative activities that improve and advance many aspects of human lives. They enable non-experts to express themselves through drawing, or help UI designers explore diverse alternatives through low-fidelity prototyping. Generating these sketches and prototypes, however, typically requires significant expertise beyond casual users and may be effortful and time-consuming even for professional users.
In this talk, I will introduce multiple deep-learning methods and systems that can generate sketches and prototypes. The generation of these artifacts is designed to be guided by annotations in familiar modalities (e.g., generating user interfaces from text descriptions). This research creates unique affordances, advances state-of-the-art of creativity support tasks, contributes benchmark metrics, and explores novel interaction paradigms in diverse domains from non-expert sketching to professional UI/UX design. These research contributions can serve as important building blocks towards future multi-modal systems that enable more effective and efficient sketching and prototyping for all.
John CANNY, canny@berkeley.edu, 510-642-9955