Zhiwen Chen

Zhiwen Chen (陈志文)

I'm currently working as a Staff Algorithm Engineer at Alibaba Group where I'm leading the PixelAI Algorithm Team of Tao Technology. Previously before 2017, I worked as a Video Analytic Researcher at Trakomatic Pte. Ltd., Singapore for several years.

I received the B.E. degree in computer science from SJTU, under the supervision of Prof. Fan Wu in 2012 and the M.E. degree in computer science from NUS in 2014.

Email / LinkedIn / CV

Research

I'm interested in computer vision, in particular, Pose Estimation, Human Reconstruction, Animatable Avatar, Virtual Try-On, etc. Below are some highlighted publications.

	GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting Hongyun Yu, Zhan Qu, Qihang Yu, Jianchuan Chen, Zhonghua Jiang, Zhiwen Chen, Shengyu Zhang, Jimin Xu, Fei Wu, Chengfei Lv, Gang Yu ACM International Conference on Multimedia (ACM MM) , 2024 paper / project page We present GaussianTalker, a novel method for audio-driven talking head synthesis based on 3D Gaussian Splatting. It outperforms existing state-of-the-art methods in talking head synthesis, delivering precise lip synchronization and exceptional visual quality. It also achieves rendering speeds of 130 FPS on NVIDIA RTX4090 GPU.
	Multi-Level Pixel-Wise Correspondence Learning for 6DoF Face Pose Estimation Miao Xu, Xiangyu Zhu, Yueying Kao, Zhiwen Chen, Jiangjing Lyu, Zhen Lei IEEE Transactions on Multimedia (TMM) , 2024 paper We present a novel framework for 6DoF face pose estimation, where 2D features extracted from images and 3D features representing 3D shape interact with each other in a transformer architecture to learn the 2D-3D correspondence.
	MVP-Human Dataset for 3D Clothed Human Avatar Reconstruction from Multiple Frames Xiangyu Zhu, Tingting Liao, Xiaomei Zhang, Jiangjing Lyu, Zhiwen Chen, Yunfeng Wang, Kan Guo, Qiong Cao, Stan Z. Li, Zhen Lei IEEE Transactions on Biometrics, Behavior, and Identity Science (TBIOM) , 2023 paper / code We present 3D Avatar Reconstruction in the wild (ARwild), which first reconstructs the implicit skinning fields in a multi-level manner.
	High-Resolution Depth Maps Imaging via Attention-Based Hierarchical Multi-Modal Fusion Zhiwei Zhong, Xianming Liu, Junjun Jiang, Debin Zhao, Zhiwen Chen, Xiangyang Ji IEEE Transactions on Image Processing (TIP) , 2022 paper We presented a novel attention-based hierarchical multi-modal fusion (AHMF) network for guided depth map super-resolution.
	Context Attention Network for Skeleton Extraction Zixuan Huang, Yunfeng Wang, Zhiwen Chen, Xin Gao, Ruili Feng, Xiaobo Li IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW) , 2022 paper We proposed an attention-based model called Context Attention Network (CANet), which integrates the context extraction module in a UNet architecture, can effectively improve the network’s ability to extract the skeleton pixels. We were evaluated 1st place on CVPR DLGC Workshop and Challenge.
	Adaptive Linear Span Network for Object Skeleton Detection Chang Liu, Yunjie Tian, Zhiwen Chen, Jianbin Jiao, Qixiang Ye IEEE Transactions on Image Processing (TIP) , 2021 paper / code We proposed adaptive linear span network (AdaLSN), and automatically configured and integrated scale-aware features for object skeleton detection.
	Simple Baseline for Single Human Motion Forecasting Chenxi Wang, Yunfeng Wang, Zixuan Huang, Zhiwen Chen IEEE International Conference on Computer Vision Workshop (ICCVW) , 2021 paper We established a simple but effective baseline for single human motion forecasting without visual and social information. We were evaluated 1st place on ICCV SoMoF Workshop and Challenge.

Achievements

These include workshops, challenges and awards.

	China Computer Federation (CCF) Technology Innovation Award Chengfei Lv, Chaoyue Niu, Shengyu Zhang, Zhiwen Chen, Fan Wu, Fei Wu China Computer Federation (CCF), 2023 We built key technology and system platform for diversified intelligent industry applications based on edge-cloud collaboration.
	1st International Workshop and Challenge on People Analysis: From Face, Body and Fashion to 3D Virtual Avatars Zhiwen Chen (Challenge Main Organizer) Workshop and challenge on ECCV, 2022 challenge We contribute a large-scale dataset, MVP-Human (Multi-View and Multi-Pose 3D Human), which contains 250 subjects. Each subject has 15 type of different poses. Each pose contains 8-view RGB images.
	The Fourth Workshop on Deep Learning for Geometric Computing Zixuan Huang, Yunfeng Wang, Zhiwen Chen Workshop and challenge on CVPR, 2022 1st place winner of Pixel SkelNetOn Track workshop / challenge
	1st Workshop, Benchmark and Challenge on Human Trajectory and Pose Dynamics Forecasting in the Wild Chenxi Wang, Yunfeng Wang, Zixuan Huang, Zhiwen Chen Workshop and challenge on ICCV, 2021 1st place winner of PoseTrack and 3DPW datasets workshop / challenge

Template copied from Jon Barron and Matiur Rahman Minar.