Dr. Boyuan Bai | Artificial Intelligence and Machine Learning | Best Researcher Award
Doctor | Beijing University of Posts and Telecommunications | China
Dr. Boyuan Bai is an emerging researcher in advanced visual computing, with a focused contribution to 3D reconstruction, Gaussian Splatting, multi-view scene modeling, and uncertainty-aware machine learning. His work integrates computer graphics, deep learning, and computational geometry to develop intelligent systems capable of producing highly accurate and stable indoor scene reconstructions. With 83 citations, 4 Scopus-indexed publications, and an h-index of 3, he is rapidly establishing a strong research footprint. Dr. Boyuan Bai’s notable scientific contribution centers on UncertainGS, an uncertainty-aware indoor reconstruction framework published in Neurocomputing (SCI/Scopus). This research introduces a novel pipeline that integrates cross-modal uncertainty prediction to guide the optimization of Gaussian Splatting. His methodological innovation improves the fidelity of reconstructed surfaces, especially in textureless or geometrically ambiguous indoor regions. His incorporation of Manhattan-world constraints into the Gaussian Splatting process represents a significant leap forward in aligning 3D surface geometry with real-world structural patterns. His research areas broadly span multi-view 3D reconstruction, Gaussian Splatting, uncertainty modeling, scene understanding, and deep reinforcement learning for geometric perception. He actively contributes to the development of next-generation 3D vision technologies, with applications in robotics, digital twins, AR/VR environments, and autonomous spatial intelligence. His work shows strong potential for large-scale deployment in real-time virtual reconstruction and simulation systems. Dr. Boyuan Bai’s scholarly output includes peer-reviewed journal publications, research project leadership, and scientific contributions that address fundamental challenges in computational imaging. His research achievements demonstrate clear innovation, technical depth, and growing influence in the fields of computer vision and graphics. Through ongoing academic collaborations and continued focus on high-impact research problems, he is emerging as a promising researcher in intelligent 3D scene modeling and uncertainty-aware visual computing.
Featured Publications
1. Bai, B., Qiao, X., Lu, P., Zhao, H., Shi, W., & others. (2025). Two grids are better than one: Hybrid indoor scene reconstruction framework with adaptive priors. Neurocomputing, 618(C). https://doi.org/10.1016/j.neucom.2024.129118
2. Huang, Y., Bai, B., Zhu, Y., Qiao, X., Su, X., Yang, L., & others. (2024). ISCom: Interest-aware semantic communication scheme for point cloud video streaming on Metaverse XR devices. IEEE Journal on Selected Areas in Communications, 42(4). https://doi.org/10.1109/JSAC.2023.3345430
3. Zhu, Y., Huang, Y., Qiao, X., Tan, Z., Bai, B., & others. (2023). A semantic-aware transmission with adaptive control scheme for volumetric video service. IEEE Transactions on Multimedia, 25. https://doi.org/10.1109/TMM.2022.3217928
4. Huang, Y., Zhu, Y., Qiao, X., Tan, Z., & Bai, B. (2021). AITransfer: Progressive AI-powered transmission for real-time point cloud video streaming. In Proceedings of the 29th ACM International Conference on Multimedia (MM ’21). https://doi.org/10.1145/3474085.3475624