Dr. Brojeshwar Bhowmick is a principal scientist heading the research in the area of Visual Computing and Embodied AI in TCS Research, Kolkata, India. His current research focuses on building interactive 3D digital representation of a physical world and humans which an embodied agent can use to reason, act, plan and collaborate with human autonomously. Before that he worked in Indian Statistical Institute and in a start-up (Videonetics). Over the years he is developing many novel solutions in variety of areas in computer vision, graphics and machine learning which includes; Neural Network aided software for diagnosis of microcalcification in mammograms(2005); Developing machine learning algorithms for intelligent video surveillance (2007); ADAS system using stereo geometry to prevents accidents (2010); 3D digital twin of Indian heritage sites like Hampi from photographs(2014-2017); one of the first adaptive talking head generation method (2020); an intelligent telepresence robot (2022); one of the first unified AI method for animating 3D loose garment of various types, topologies, and materials over 3D body (2023); one of the first intelligent task planning method for a housekeep robot (2024).
He did his PhD from the department of Computer Science and Engineering in Indian Institute of Technology Delhi in the area of Computer Vision and did his B.Tech in Computer Science and Engineering from the University of Kalyani. He was a visiting PhD student at the Graphics, Vision and Video group in the Max Planck Institute Informatik, Germany.
He is a fellow of IETE, senior member of IEEE and associate editor of Springer SNCS journal. He has served as an organising committee member and program committee member of several conferences like ICPR, ISBI, ICVGIP, CVPR, AAAI, IJCAI, WACV, ICLR etc.. He is also a reviewer of several journals.
He is a recipient of the best paper award in ICVGIP 2o18 and 2021, best demo award at ICDCN 2020, patent champion award at TCS Research in 2016 and special mention Young IT Professional award by Computer Society of India in 2008. He has published nearly 70 research papers in the areas of Computer Vision, Graphics, AI and Robotics and has more than 30 granted patents.
The topics of his research includes 3D Computer Vision, Computer Graphics, Multi-view Geometry, Large-scale 3D Reconstruction, 3D human digitization, Deep Reinforcement Learning and Meta-Learning.