Roni Sengupta

University of North Carolina at Chapel Hill

Papers

Total Citations

H-Index

About

Roni Sengupta is a rising researcher in computer vision and robotics, whose work focuses on advancing 3D scene understanding from limited visual data. His key research areas include monocular depth estimation, multi-view perception, and medical imaging analysis. Sengupta’s major contributions lie in developing novel approaches that leverage geometric and physical priors to overcome the inherent ambiguities of single-view depth prediction. His 2024 paper, "Joint Depth Prediction and Semantic Segmentation with Multi-View SAM," introduces a multi-task framework that exploits multiple views—common in robotics—to jointly predict depth and semantic labels, achieving more robust and accurate scene understanding than monocular methods. This work has already garnered 10 citations, signaling its impact on the field. Additionally, his paper "Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videos" (8 citations) pioneers the use of lighting cues specific to endoscopic environments to improve depth perception, a critical step for minimally invasive surgery. Sengupta’s research bridges the gap between theoretical computer vision and practical applications in robotics and medicine, making him a notable figure in the next generation of vision researchers.