Lei Zhong

I'm a PhD student in the School of Informatics at the University of Edinburgh, supervised by Prof. Changjian Li. Before that, I received a Master's degree from Nankai University, supervised by Prof. Shao-ping Lu, and a Bachelor's degree from Southwest University.

Email  /  Scholar  /  Twitter  / 

profile photo

Research

My research interests lie at the intersection of vision and graphics. Recently, I have been focusing on 3D human motion modeling and generation. Some papers are highlighted.

ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learning
Yi Yang, Lei Zhong, Huiping Zhuang,
WACV 2025
paper / project

This paper introduce a novel Recursive Fusion model, dubbed ReFu, designed to integrate point clouds and meshes for exemplar-free 3D Class-Incremental Learning.

SMooDi: Stylized Motion Diffusion Model
Lei Zhong, Yiming Xie, Varun Jampani, Deqing Sun, Huaizu Jiang
ECCV 2024
paper / project / code

This paper introduces SMooDi, which enables stylized motion generation by incorporating style motion sequences into a text-conditioned human motion generation model.

OmniControl: Control Any Joint at Any Time for Human Motion Generation
Yiming Xie, Varun Jampani, Lei Zhong, Deqing Sun, Huaizu Jiang
ICLR 2024
paper / project / code

This paper introduces OmniControl, which incorporates flexible spatial control signals into a text-conditioned human motion generation model based on the diffusion process.

Aesthetic-guided Outward Image Cropping
Lei Zhong, Feng-Heng Li, Hao-Zhi Huang, Yong Zhang, Shao-Ping Lu, Jue Wang
SIGGRAPH ASIA 2021 (ACM Transactions on Graphics)
paper

This paper proposes an aesthetic-guided outward image cropping method that extends beyond the image border to achieve compositions unattainable with previous methods.

A Graph-Structured Representation with BRNN for Static-based Facial Expression Recognition
Lei Zhong, Changmin Bai, Jianfeng Li, Tong Chen, Shigang Li, Yiguang Liu
FG 2019 (IEEE Conference on Automatic Face and Gesture Recognition)
paper

This paper presents a graph-structured representation with BRNN for static-based facial expression recognition, achieving improved accuracy in recognizing facial expressions.