Aaron Hertzmann – ACM SIGGRAPH HISTORY ARCHIVES

Aaron Hertzmann

Next: »
« Previous:


Most Recent Affiliation(s):


  • Adobe Inc., Principle Scientist

Other / Past Affiliation(s):


  • University of Toronto
  • New York University
  • University of Washington

Location:


  • Washington, United States of America

Bio:

  • SIGGRAPH 2024

    Aaron’s groundbreaking contributions to the field of NPR are widely recognized, particularly his early work on painterly rendering of images and video. His innovative techniques for line drawing of 3D models continue to influence the field today. Aaron’s seminal Image Analogies paper spearheaded a new era of machine learning applied to image authoring and stylization. Its long-lasting impact extends to recent image editing methods using Generative Adversarial Networks and diffusion models.

    As one of the pioneering researchers at the intersection of computer graphics and machine learning, Aaron has made significant contributions to character animation with models learned from motion-capture data, as well as capturing non-rigid motion from video and rotoscoping. In addition to ML-based approaches, Aaron’s work in physics-based human motion control laid the groundwork for the subsequent rise of reinforcement learning for physics-based animation. In the realm of computational photography and image editing, Aaron’s contributions include advancements in image deblurring, portrait segmentation, depth-aware editing, and GAN controls. Aaron also introduced early machine learning approaches for graphic design and for geometry processing.

    Beyond his technical contributions, Aaron is recognized as an influential thinker across computer graphics and computer vision. His position articles on the science of art and generative AI art offer valuable insights into the evolving landscape of art-making processes, drawing from art history, philosophy, and psychology. Moreover, Aaron’s theories on human visual perception of pictures have challenged conventional understanding, providing explanations for phenomena unexplained by existing linear perspective theories. Aaron’s intellectual contributions have sparked debates and discussions across the interdisciplinary communities of computer science and art, enriching our understanding of the complex relationship between technology and creativity.

    Aaron received a Bachelor degree in Computer Science and Art at Rice University and a Ph.D. degree in Computer Science from New York University in 2001 under the supervision of Ken Perlin and Denis Zorin. He was a Professor of Computer Science at the University of Toronto from 2003-2013, and since 2012 has been at Adobe, where he became a Principal Scientist in 2016. Throughout his career, Aaron has consistently provided his professional services to his communities, including as co-organizer of NPAR 2004, as the inaugural SIGGRAPH 2022 Conference Papers Director for the conference track that he advocated for, and as the Editor-in-Chief of Foundations and Trends in Computer Graphics and Vision.

    Previous Biography

    Aaron Hertzmann is a Principal Scientist at Adobe, Inc., and an Affiliate Professor at University of Washington. He received a BA in Computer Science and Art & Art History from Rice University in 1996, and a PhD in Computer Science from New York University in 2001. He was a professor at the University of Toronto for 10 years, and has worked at Pixar Animation Studios and Microsoft Research. He has published over 100 papers in computer graphics, computer vision, machine learning, robotics, human-computer interaction, and art. He is an ACM Fellow and an IEEE Fellow.

Course Organizer:


Learning Category: Jury Member:


Award(s):