Max Robotics — Global Service Robot Directory + US Certification

About

Shengjun Tang is a leading researcher in indoor 3D modeling, computer vision, and spatial intelligence, with a focus on bridging the gap between raw sensor data and actionable semantic understanding. His work centers on solving the fundamental challenges of indoor scene reconstruction and localization, particularly in dynamic and complex environments. Tang’s major contributions include pioneering the use of consumer-grade RGB-D cameras for indoor 3D modeling, as evidenced by his highly cited survey on the topic (25 citations), which has become a key reference for researchers and practitioners alike. He has also advanced the field of visual localization with innovative end-to-end deep learning approaches, such as TransCNNLoc (9 citations), which achieves pixel-level 2D-to-3D pose estimation in dynamic indoor scenes. Additionally, Tang has developed automated methods for generating labeled indoor point clouds from BIM models (4 citations), addressing the critical need for large-scale training datasets in deep learning. His recent work on BIM-based indoor navigation using ARCore (4 citations) demonstrates a practical integration of building information models with augmented reality for precise, real-time localization. With a growing citation impact, Tang’s research is shaping the future of indoor robotics, AR navigation, and smart building applications.