Static Scenes with Dynamic Perceptions

Static Scenes with Dynamic Perceptions

Authors

Presenter(s)

Kunal Agrawal

Comments

10:20-10:40, LTC Studio

Files

Description

In this paper, we explore how computers can recognize motion illusions in static images—pictures that trick our eyes into seeing movement. To study this, we created a new dataset called MISS, which includes images with and without motion illusions. We tested advanced deep learning models to see how well they could identify these illusions and also checked whether color plays an important role. Our results show that these models are good at spotting motion illusions, especially when the images are in color. This highlights the importance of color in helping machines understand motion in still pictures.

Publication Date

4-23-2025

Project Designation

Graduate Research

Primary Advisor

Tam Nguyen

Primary Advisor's Department

Computer Science

Keywords

Stander Symposium, College of Arts and Sciences

Institutional Learning Goals

Community; Diversity; Scholarship

Static Scenes with Dynamic Perceptions

Share

COinS