Sep 7, 2023 Thursday
Last several years have witnessed the drastic growth of needs for 3D content generation and reconstruction, which are important for achieving the intelligent systems, such as VR/AR and robotics. In particular, neural rendering techniques, such as Neural Radiance Fields (NeRF), are the pivotal technical bracket for 3D generation and reconstruction. In this talk, I will mainly share two lines of research ongoing in our research group: 1) explicit NeRF acceleration and its potential boost to real-time RGB NeRF-SLAM systems; 2) generating 3D contents from texts and visual prompts based on diffusion models and NeRF. Finally, I will wrap up this talk by sharing some challenges and future directions that are worth further explored.
September 7th, 2023, Thursday
628 334 1826 (PW: 234567)
Dr. Addison Lin WANG
Assistant Professor, AI Thrust, INFH,HKUST(GZ)
Dr. Wang is currently an Assistant Professor in the Artificial Intelligence Thrust, a joint Assistant Professor in the Computational Media and Arts (CMA) Thrust, HKUST-GZ and an Affiliate Assistant Professor in the Computer Science and Engineering Department at HKUST. He also serves as the Coordinator for the Undergraduate Program of Artificial Intelligence Thrust. Dr. Wang received his Ph.D. degree in the field of Artificial Intelligence (with highest PhD research award) from Korea Advanced Institute of Science and Technology (KAIST). He was a visiting researcher at Imperial College London, UK, from 2020 to 2021. Dr. Wang’s research interests include computer/robotic vision, multi-modality sensing, intelligent systems (XR/metaverse, robotics), and human-AI interaction. He has published over 40 high-quality papers in top-tier journals and conferences related to AI, robotics, and human-computer interaction in the past several years, some of which have been applied in industry. He has served as a program committee member for conferences and journals related to artificial intelligence, computer vision, and robotics, such as CVPR, IEEE TPAMI, IEEE RA-L, etc. For more details, please feel free to visit his lab homepage at: vlislab22.github.io/vlislab/.