John Taylor, Professor of Economics at Stanford University and developer of the "Taylor Rule" for setting interest rates | Stanford University
John Taylor, Professor of Economics at Stanford University and developer of the "Taylor Rule" for setting interest rates | Stanford University
Maneesh Agrawala, a computer scientist specializing in AI tools for creating and editing audio and video, serves as the director of the Brown Institute for Media Innovation and is the Forest Baskett Professor in the School of Engineering at Stanford University. His work focuses on supporting and evolving storytelling through technological advancements.
“Stories are at the heart of human culture and we often use images and video to communicate ideas, information, our feelings, and emotions to one another through visual means. I believe that tools that can facilitate creation of this kind of media can be really beneficial to human culture,” said Agrawala. “The more we can express ourselves and tell our stories to other people, I think the better off we’ll be.”
Agrawala discussed his motivations with Stanford Report: “Fundamentally, I value the idea of making it easier for people to express themselves. That is at the core of almost everything we do in my research group. I’ve been interested in visual communication and how we make visual art for a long time.”
His interest in computer graphics began during his undergraduate studies at Stanford. He emphasized that much of his current work aims to ease the process of turning ideas into visual content.
“The primary intended application for the tools we are building is to facilitate the creation of visual stories,” he noted. Companies like Adobe, Pixar, Google, and YouTube have adopted some of these tools to aid artists and end-users.
Agrawala's projects include augmented reality filters on social media platforms, digital tools for lighting adjustments irrespective of skin tone or real-world conditions, background modifications on video calls, "ControlNet" for spatial placement in text-to-image AI-generated content, and advanced video/audio editing via text transcripts.
Addressing concerns about deepfakes, Agrawala explained: “The definition of deepfakes moves around a lot... It’s about lying. Humans can use technology to create lies or we can use it for positive purposes.” He stressed that while technology plays a role in misinformation issues, human behavior is a critical factor.
Future developments aim at improving control over generative AI models by integrating not just text but also other images to guide outputs more precisely. Understanding expert processes will help develop user-friendly interfaces for these tools.
Agrawala also holds an affiliation with the Stanford Institute for Human-Centered Artificial Intelligence (HAI).
©Copyright Stanford University
Alerts Sign-up