Sunando Sengupta

Papers

Total Citations

153

H-Index

About

Sunando Sengupta is a leading researcher in computer vision and robotics, whose work bridges the critical gap between 2D image understanding and 3D spatial reconstruction. His primary research areas include semantic 3D scene understanding, simultaneous localization and mapping (SLAM), and probabilistic graphical models for holistic scene interpretation. Sengupta’s most influential contribution is his pioneering work on unifying recognition, reconstruction, and representation within a single framework. His seminal 2013 paper, "Mesh Based Semantic Modelling for Indoor and Outdoor Scenes" (101 citations), introduced a novel approach to semantic reconstruction that captures rich 3D information often lost in traditional image-domain object labelling. He further advanced the field with his 2015 paper, "Semantic octree: Unifying recognition, reconstruction and representation via an octree constrained higher order MRF" (52 citations), which proposed an elegant octree-based higher-order Markov Random Field model. This work seamlessly integrates multi-resolution image labelling with volumetric 3D mapping, enabling more robust and comprehensive scene understanding for applications ranging from autonomous navigation to augmented reality. Sengupta’s research continues to shape how machines perceive and interact with complex environments.