CSAIL Event Calendar

Towards Automatic Visual Content Creation

Title: Towards Automatic Visual Content Creation

Abstract:
Computer graphics has been very successful. However, two important problems still remain unsolved. Firstly, the ability for ordinary people to quickly generate high quality image-based media remains elusive. Secondly, realistic images or animations require high quality content (such as detailed 3D models and their materials), which is tedious and manually intensive to prepare even for professionals.

This talk introduces our recent work toward these challenges to bridge the gap between ordinary people and graphics professionals, and to make 3D content easy to create. We take a data-driven approach for media synthesis to allow a novice user to easily create high quality visual media simply by specifying its content. The user needs only to provide simple high level input such as sketches and text labels. Our algorithm can automatically search for suitable image elements, and generate realistic output images or even animations. We also develop systems to automate the process of 3D content creation. We build image-based modeling systems to model large scale outdoor scenes such as trees, buildings and streets. We also develop photogeometric algorithms to precisely capture both 3D shape and surface reflectance.

Bio:
Ping Tan received the BS degree in Applied Mathematics from the Shanghai Jiao Tong University in China in 2000 and the PhD degree in Computer Science and Engineering from the Hong Kong University of Science and Technology in 2007. He joined the Department of Electrical and Computer Engineering at the National University of Singapore as an assistant professor in 2007. He received the MIT TR35@Singapore award in 2012. His research interests include computer vision and computer graphics. He is a member of the IEEE and ACM.

See other events happening in June 2012