Beyond Image Generation - Diffusion Models for 3D Pose and Mesh Recovery

[CFAR Rising Star Lecture Series]
Beyond Image Generation - Diffusion Models for 3D Pose and Mesh Recovery (Hybrid event) by Liu Jun
2 Feb 2024 | 10.00am (Singapore Time)

Artificial intelligence generated content (AIGC) has attracted a lot of research attention recently. The great success of the text-to-image generation models is partially due to the emergence of the diffusion models. Generally, diffusion models rely on the progressive noising and denoising steps based on the Gaussian distribution. However, in some scenarios, the distribution of the noise is non-Gaussian. In this talk, Dr Liu Jun will introduce two techniques capable of handling non-Gaussian-distribution noise. He will also share about their efficacy in 3D pose estimation and 3D mesh recovery tasks, showcasing the techniques’ state-of-the-art results in these domains.

Dr Liu Jun
Assistant Professor
Information Systems Technology and Design (ISTD)
Singapore University of Technology and Design (SUTD)

Dr Liu Jun is an Assistant Professor in SUTD. His research interests include computer vision and artificial intelligence. Dr Liu’s works have been published in premier computer vision journals and conferences, including TPAMI, CVPR, ICCV, and ECCV and he has a Google Scholar citation count of 11,400.  Dr Liu is an Associate Editor of IEEE Transactions on Image Processing and IEEE Transactions on Biometrics, Behaviour, and Identity Science, IET Image Processing, IET Computer Vision, and Visual Intelligence, and serves/has served as an Area Chair of CVPR, ECCV, ICML, NeurIPS, ICLR, MM, and WACV, etc.