Speaker:

Andrew Owens, Associate Professor of Computer Science at Cornell Tech

Talk Title:

Generating Multi-View Visual Illusions

Date and Location:

Thursday, January 29, 2026

3–4 p.m.

BA 5166 (DGP seminar room) and online. Zoom registration link for virtual attendance.

Reception to follow

There is no registration required to attend this event in person. However, seating is limited, so arriving early is recommended.

Abstract:

I will present methods for generating multi-view visual illusions: images that change their appearance upon a transformation, such as a flip or a rotation. Creating these images is a challenging problem because it requires arranging visual elements such that they can be understood in multiple ways. I will show that we can use off-the-shelf diffusion models to solve this task without additional training, by making simple changes to the reverse diffusion process. First, I will present a method for generating "visual anagrams", images whose pixels can be permuted to form another image. This enables us to make a number of illusions, such as jigsaw puzzles that can be solved in two different ways. I will then present an extension of this approach that allows us to control each individual linear component of an image, given a factorization of an image into a sum of linear factors. This makes it possible to generate images whose appearance varies by viewing distance or illumination conditions. Finally, I will discuss another way to extract surprising capabilities from off-the-shelf diffusion models: I will show that we can perform zero-shot tracking by simply prompting a video diffusion model to visually mark points as they move over time, thereby converting a video generator into a point tracker.

Biography:

Andrew Owens is an associate professor of computer science at Cornell Tech. Prior to that, he was an assistant professor at the University of Michigan and a postdoctoral scholar at UC Berkeley. He obtained a Ph.D. in Electrical Engineering and Computer Science from MIT in 2016. He is a recipient of a Sloan Research Fellowship, an NSF CAREER Award, and a Computer Vision and Pattern Recognition (CVPR) Best Paper Honorable Mention Award.