AI & Fundamentals

Reconstructing and Synthesizing 3D Scenes - Young Min Kim, Associate Professor, Seoul National University

Please register for this event here to receive the Zoom Link.
 

Abstract:

Representing the 3D scenes can incur various interesting real-world applications. However, the intelligent module for everyday 3D environments is not trivial. While most powerful AI algorithms rely on abundant data, 3D data is highly irregular, of low quality, and scarce. In addition, we have to be clever to handle a large amount of memory and computation to store and process 3D information. In this talk, I will discuss how we can combine different input modalities and neural architecture designs to handle 3D scenes, namely reconstruction, and synthesis. The first half of the talk introduces recent works on reconstructing scenes from real-world capture. The second half will focus on generating diverse and high-quality 3D scenes. Eventually, the techniques can perceive and synthesize realistic daily environments and assist humans.

Bio:

Young Min Kim is an associate professor at Seoul National University, where she leads the 3D vision lab (3d.snu.ac.kr). She is also currently a visiting scholar at University of California San Diego. She received the B.S. from Seoul National University in 2006 and the M.S. and Ph.D. degrees in electrical engineering from Stanford University in 2008, and 2013 respectively. Before joining SNU, she was a Senior Research Scientist at Korea Institute of Science and Technology (KIST). From 2016 to 2018, she was a Visiting Researcher in the Center for Computational Visualization at the University of Texas at Austin. Her research interest lies in 3D vision, where she combines algorithms in computer vision, graphics, and robotics to solve practical problems.

Please register for this event here to receive the Zoom Link.

You can see the other CVPR 2023 UBC events here.