In honor of his technical achievements, Noah Snavely was recently named a 2023 Association for Computing Machinery (ACM) Fellow. ACM, the largest and most prestigious society of computing professionals, recognizes the top 1% of members for their outstanding accomplishments in computing and information technology through its fellowship program.

“I never imagined receiving such an honor when I was starting out,” he reflects. Snavely’s journey from academia to entrepreneurship and back epitomizes two core concepts that Cornell Tech offers: the academic rigor of a Cornell/Technion education coupled with having access to critical startup infrastructure and resources.

From his undergraduate days at the University of Arizona to his pioneering role as a leading researcher in the field of computer vision at Cornell Tech, Snavely has had a journey marked by groundbreaking discoveries and an unyielding drive to redefine the boundaries of what is achievable in this emerging research domain.

Snavely’s foray into computer vision – a field focused on developing algorithms to enable computers to interpret and understand visual information from images or videos – began during his time at Arizona.

“I was always interested in computer graphics, but then one of my undergrad advisors said, ‘Why not explore computer vision?’ So I thought I’d give that a try,” he recalls.

During his PhD studies at the University of Washington, Snavely developed new software capable of constructing intricate 3D models from internet photos—a feat previously unheard of in the field.

This research eventually led to a collaborative entrepreneurial venture with his wife, which was  later acquired by Google, where Snavely then spent several years focusing on industry innovation. However, his passion for pushing the boundaries of computer vision ultimately drew him back to academia, finding a home at Cornell Tech.

At Cornell Tech, Snavely’s work spans a diverse range of projects, from mapping technologies to immersive VR experiences. “My expertise in generative AI for 3D models is reshaping how we interact with digital spaces,” he explains. Snavely’s recent research on synthesizing entire 3D worlds from text prompts has exciting real-world implications across various industries such as game design and filmmaking.

As Snavely contemplates the future of computer vision, he acknowledges the uncertainties that lie ahead. “Rapid advancements in generative AI raise questions about the ethical implications of autonomous content creation,” he observes.

While the prospect of computers autonomously generating entire movies from scripts is both intriguing and concerning, Snavely, a movie buff himself, remains steadfast in his commitment to leveraging technology for positive change and pushing the boundaries of possibility in the field of computer vision.