Shape Representations from Generative Models to 3D Deep Learning
Public · Hosted by Boston University ACM-W Student Chapter
Time: Thursday 08/27/2020 at 4 PM
Type: Online Event
Registration link: https://www.facebook.com/events/679185716010051/
This talk will discuss and present a collection of approaches for processing 3D data towards generative models for shape representations. We will start with building hierarchical, parametrized, and explainable (i.e., not deep) shape representations (grammars) from several shape formats, then explore their artistic and computational benefits for generative approaches. Then we will shift gears with an introduction to deep generative models, followed by an overview of such models in 3D, and their progression on voxels, point clouds, meshes, graphs, and other 3D representations. We will also investigate how similar constructions can be exploited in extracting shape abstractions in the context of 3D deep learning. The talk will conclude with some sneak peeks of our AR/VR productions from the world’s largest volumetric capture stage at Intel Studios, as an example of real-world use cases of such AI approaches.
Dr. Ilke Demir earned her Ph.D. in Computer Science from Purdue University, focusing on 3D vision approaches for generative models, urban reconstruction and modeling, and computational geometry for synthesis and fabrication. Afterward, she joined Facebook as a Postdoctoral Research Scientist working with Ramesh Raskar from MIT. Her research included human behavior analysis and deep learning approaches in virtual reality, geospatial machine learning, and 3D reconstruction at scale. In addition to her publications in top-tier venues (SIGGRAPH, ICCV, CVPR), she has organized workshops, competitions, and courses at the intersection of deep learning, computer vision, and graphics. She has received several awards and honors such as Jack Dangermond Award, Bilsland Dissertation Fellowship, IEEE Industry Distinguished Lecturer, and GHC Fellow, in addition to her best paper/poster/reviewer awards. Currently, she is a Senior Research Scientist at Intel, leading the computer vision and deep learning research in the world’s largest volumetric capture stage.