Creating 3D models from casual camera captures enables various creative and cognitive applications for AR/VR, Computational Photography, Robotics, and Medical Imaging. Nonetheless, the underlying 'engines' propelling these 3D models—comprising the hardware systems for capture and machine learning models—are often expensive to build, thereby constraining widespread accessibility. In this talk, I will discuss my group’s effort to develop efficient and accessible 3D models. The first part of the talk will focus on developing lightweight and personalized 3D generative models for facial reconstruction and relighting. The last part of the talk will focus on developing efficient 3D reconstruction algorithms that combine both camera and lighting variations for objects, scenes, and endoscopy images.
Roni Sengupta is an Assistant Professor of Computer Science at the University of North Carolina at Chapel Hill. Her research interest lies at the intersection of Computer Vision and Computer Graphics. Previously she was a Postdoctoral Research Associate at Paul G. Allen School of Computer Science and Engineering at the University of Washington, Seattle from 2019-2022 after finishing her PhD from the University of Maryland, College Park. Her work on Background Matting received Best Student Paper Honorable Mentions at CVPR 2021 (Top 7 papers out of 1600 accepted) and has been adopted by various companies, e.g. Microsoft, Inter-State Studio, etc.