Stony Brook University Computer Science

Prof. Jongseong Brad Choi from ME Department will be giving a talk on "Neural Rendering toward Hyper-Realistic Digital Twins: Bridging AI andHardware".

Please find the seminar details below:
Title: Neural Rendering toward Hyper-Realistic Digital Twins: Bridging AI and Hardware
Date & Time: Friday, November 14, 2 PM
Venue: B204

Abstract
Artificial intelligence (AI) is evolving toward hardware integration. The conventional paradigm of AI has predominantly centered on software models that process and learn from vast amounts of curated data. In contrast, the field of engineering is inherently hardware-oriented, operating within complex physical environments where systems must endure long-term exposure to external factors. Recently, AI has been evolving beyond data-centric computation toward agentic AI and physical AI, emphasizing its integration into hardware systems. The seminar will showcase core methodologies, real-world applications, and future research directions, highlighting the transformative impact of AI-powered predictive tools in engineering, and infrastructure, focusing on ongoing projects at the MEIC Lab (Mechanical Systems with Intelligence and Computer Vision Laboratory) led by Prof. Choi. Specifically, this presentation explores an integrated framework that leverages neural rendering and 3D perception & control, and multi-view geometry to achieve high-fidelity scene reconstruction and semantic understanding from complex, heterogeneous data sources such as RGB, LIDAR, MR sensors. MICRO-Splatting pipeline that we developed transforms incomplete or unstructured data into photorealistic digital twin models enabling remote sensing and human-machine collaboration. This further highlights the role of Physics-Informed Neural Networks (PINNs) in embedding physical constraints into data-driven models, enabling more accurate and physically consistent predictions for engineering tasks focusing on PHM, reliability engineering for Electric Vehicles. The talk aims to bridge the gap between cutting-edge computer vision research and its operational deployment for assessment engineering, providing insights into future directions where physics-based modeling and deep learning synergistically push the boundaries of visual intelligence.

Speaker Bio
Jongseong Brad Choi is an Assistant Professor in the Department of Mechanical Engineering at the State University of New York, Korea (SUNY Korea), Stony Brook University, where he directs Mechanical Systems with Intelligence and Computer Vision Laboratory (MEIC Lab) with 6 Ph.D. and 6 master’s students. He earned his Ph.D. in Mechanical Engineering from Purdue University, West Lafayette, and both his M.S. and B.S. degrees from the University of Mississippi. Dr. Choi’s research aims to advance the integration of artificial intelligence with hardware engineering by combining computer vision, multimodal sensing, neural rendering, 3D perception, and digital twin technologies. Since 2017, he has led pioneering research projects supported by the NSF, NASA, the European Union, and the NRF, resulting in over 90 publications in journals and conferences on visual intelligence and 3D perception. His research portfolio features extensive collaborations with government and industry partners, with cumulative grant funding exceeding USD 2.5 million (sole portion) over the past five years. He has received multiple honors, including the Prospective Scientist Awards from KSME (2025) and KSPHM (2023). Dr. Choi currently serves as an Associate Editor for the ASME Journal of Mechanisms and Robotics and as Chair of a committee within the KSME. More information can be found on his website: https://www.meic-lab.com/.