Shuai Shen

I am a fifth-year Ph.D. student in the Department of Automation at Tsinghua University, advised by Prof. Jiwen Lu and Prof. Jie Zhou. Prior to that, I received my B.S. degree in the Department of Automation at Tsinghua University in 2019.

My research interests lie in computer vision and deep learning, particularly in face clustering and face synthesis.

I anticipate graduating in June 2024, and now I am looking for a postdoctoral position. If you are interested in my research, feel free to drop me an e-mail shens19[AT]mails.tsinghua.edu.cn.

Email  /  GitHub  /  Google Scholar

We develop a hierarchical GCN training paradigm and the adaptive Node Intimacy strategy for adaptive neighbor interaction.

We propose a Spatially-adaptive Dual-driven NeRF (SD-NeRF) to model the spontaneous facial motions with audio-to-lip mapping into the facial radiance field for vivid talking head animation.

We propose an attribute hallucination framework named CLIP-Cluster to narrow the intraclass variance caused by different face attributes for face clustering.

We model the talking head synthesis as an audio-driven temporally coherent denoising process based on the Diffusion Model, which can be generalized across different identities.

A NeRF-based few-shot talking head synthesis method, which can rapidly generalize to an unseen identity with few training data.

It is the first face clustering method to train on very large-scale graph with 20M nodes, and achieve superior inference results on 12M testing data.

Website Template