FRIDA: Supporting Artistic Communication in Real-World Image Synthesis Through Diverse Input Modalities - Robotics Institute Carnegie Mellon University
Loading Events

PhD Speaking Qualifier

December

8
Thu
Peter Schaldenbrand PhD Student Robotics Institute,
Carnegie Mellon University
Thursday, December 8
12:00 pm to 1:00 pm
NSH 4305
FRIDA: Supporting Artistic Communication in Real-World Image Synthesis Through Diverse Input Modalities

Abstract:
FRIDA, a Framework and Robotics Initiative for Developing Arts, is a robot painting system designed to translate an artist’s high-level intentions into real world paintings. FRIDA can paint from combinations of input images, text, style examples, sounds, and sketches. Planning is performed in a differentiable, simulated environment created using real data from the robot allowing gradient descent to be used to generate high-fidelity painting plans. Vision is used to perceive the painting progress throughout creation to respond to and embrace the stochastic nature of paint as a medium. https://pschaldenbrand.github.io/frida/

Committee:
Jean Oh (Chair)
Jim McCann
Jun-Yan Zhu
Michelle Zhao