The initial stage of a design process is often highly exploratory and unexpected, involving activities such as brainstorming, seeking inspiration, sketching, and planning.
These activities require prior knowledge, creativity, and design skills.
Can computers participate in such a highly creative process, assisting humans in developing and exploring design ideas?
In this talk, I will share some of my recent research, which explores this question from various perspectives.
I will demonstrate how my work leverages recent developments in large vision-language models to drive advancements in this field.
Specifically, I will discuss the automatic generation of visual abstractions and sketches from images (CLIPasso and CLIPascene).
I will also demonstrate how such models can be used in typography to create semantic word-as-image illustrations, and in design, to decompose a visual concept, represented by a collection of images, into distinct visual elements, facilitating exploration and inspiration.
ael Vinker is a PhD student at Tel Aviv University, advised by Professors Daniel Cohen-Or and Ariel Shamir. Her research lies at the intersection of computer graphics and art, focusing on generative models. Yael has received two SIGGRAPH Best Paper Awards and an Honorable Mention Award for her works 'CLIPasso', 'Inspiration Tree', and 'Word-as-Image'. Her honors include the Fulbright Postdoctoral Fellowship, the Blavatnik Prize for outstanding Israeli doctoral students in computer science, and the VATAT Scholarship for outstanding female PhD candidates. She earned her BSc and MSc from The Hebrew University of Jerusalem.