معرفی
Roni Sengupta is an Assistant Professor in the Department of Computer Science at the University of North Carolina at Chapel Hill, where she leads the Spatial & Physical Intelligence (SPIN) Lab. Her academic journey includes a Ph.D. from the University of Maryland (2019), a postdoctoral position at the University of Washington (2019-2022), and an undergraduate degree in Electronics and Tele-Communication Engineering from Jadavpur University in India.
Her research lies at the intersection of Computer Vision and Computer Graphics, with four primary themes:
- Inverse Rendering: Recovering physical scene properties like geometry, material reflectance, and lighting
- 3D Perception from Endoscopy: Monocular depth estimation and SLAM for medical imaging applications
- Inverse Physics: Recovering 3D geometry and physical properties from sparse video inputs
- Generative Facial Editing: Developing personalized, training-free methods for facial attribute manipulation
Dr. Sengupta's publication record shows a clear trajectory toward increasingly sophisticated inverse problem solving, with recent work (2023-2025) focusing on neural approaches to inverse rendering, medical imaging applications, and personalized generative models. Her research demonstrates strong interdisciplinary connections between computer vision, graphics, and medical applications.
Her scientific recognition includes:
- NIH NIBIB Trailblazer Award for New and Early Stage Investigators (2024)
- UNC Junior Faculty Development Award (2024)
- UNC CS Student Association Excellence in Teaching Award (2023)
- CVPR Best Student Paper Honorable Mentions (2021)
Dr. Sengupta actively mentors a diverse team of researchers, including 5 current PhD students, 3 MS students, and several undergraduates. Her former students have gone on to positions at Google, Kitware, Databricks, and Capitol One. She has secured significant research funding, with recent work supported by NIH and industry partners. Her teaching portfolio includes undergraduate and graduate courses in computer vision, 3D generative models, and neural rendering.
The SPIN Lab maintains strong industry connections, with research collaborations and technology adoption by Microsoft, NVIDIA Research, and Snapchat Research. The lab's work on background matting has been particularly influential, receiving recognition at CVPR 2021 and being adopted by multiple companies.
