Zhening Liu

Zhening Liu

Hi. I am a ~~first-~~second-year Ph.D student at Department of Electronic and Computer Engineering in Hong Kong University of Science and Technology, supervised by Prof. Jun Zhang. Before this, I obtained my B.S. from Harbin Institute of Technology, Shenzhen, in Electronic and Information Engineering, supervised by Prof. Yufei Jiang.

Email / Scholar / Github

Research

I am currently interested in deep learning and edge AI, especially towards efficient and effective data representation & compression, and 3D/4D spatial reconstruction & generation.

	Dynamics-Aware Gaussian Splatting Streaming Towards Fast On-the-Fly Training for 4D Reconstruction Zhening Liu, Yingdong Hu, Xinjie Zhang, Jiawei Shao, Zehong Lin, Jun Zhang arXiv, 2024 Project Page \| Video Three-stage pipeline for dynamic free-viewpoint video streaming based on 3DGS, supporting on-the-fly training and per-frame streaming.
	Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model Zhening Liu, Xinjie Zhang, Jiawei Shao, Zehong Lin, Jun Zhang European Conference on Computer Vision (ECCV), 2024 Paper \| Code \| Video A bidirectional stereo image compression architecture with 3D codec, symmetric attention module, and cross-dimensional entropy model.
	MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes Xinjie Zhang, Zhening Liu, Yifan Zhang, Xingtong Ge, Dailan He, Tongda Xu, Yan Wang, Zehong Lin, Shuicheng Yan, Jun Zhang arXiv, 2024 Compact 4DGS representation for dynamic space reconstruction with low storage overhead and high rendering quality.
	EVA-Gaussian: 3D Gaussian-based Real-time Human Novel View Synthesis under Diverse Camera Settings Yingdong Hu, Zhening Liu, Jiawei Shao, Zehong Lin, Jun Zhang arXiv, 2024 Project Page Generalizable 3DGS-based holographic human reconstruction method supporting sparse input and real-time inference.
	CAMSIC: Content-Aware Masked Image Modeling Transformer for Stereo Image Compression Xinjie Zhang, Shenyuan Gao, Zhening Liu, Jiawei Shao, Xingtong Ge, Dailan He, Tongda Xu, Yan Wang, Jun Zhang Association for the Advancement of Artificial Intelligence (AAAI), 2025 A stereo image compression pipeline based on Masked Image Modeling providing fast coding speed.
	Low-complexity Precoding-aided CFO Estimation for ICA-based MIMO OFDM Systems in URLLC Zhening Liu, Yufei Jiang, Xu Zhu, Sumei Sun IEEE Transactions on Communications (TCOM), 2024 High spectral efficiency precoding-aided CFO estimation and channel equalization paradigm requiring no pilot.

Activity

2024-Sep I was honored to be a speaker at the ECE Future Leader Departmental Seminar.
2024-Sep I presented a poster at the IEEE Hong Kong 6G Wireless Submit.
2024-Jul I gave a talk at the CCF Greater Bay Area Postgraduate Academic Forums, in Guangdong University of Technology, Guangzhou.