Huiming Zheng

Peking University Shenzhen Hospital, Peking University

Papers

Total Citations

H-Index

About

Huiming Zheng is a leading researcher in point cloud compression, with a focus on balancing efficiency and semantic fidelity for emerging applications like autonomous driving, virtual reality, and robotics. Their work addresses the critical challenge of transmitting massive 3D point cloud data without losing the semantic details essential for both human perception and machine vision tasks. Zheng’s most-cited paper, "ROI-Guided Point Cloud Geometry Compression Towards Human and Machine Vision" (2024, 44 citations), pioneers a region-of-interest (ROI) approach that prioritizes bit allocation to preserve crucial foreground features while achieving high compression ratios. Building on this, "Semantic-Aware Visual Decomposition for Point Cloud Geometry Compression" (2024, 25 citations) further refines the technique by encoding ROI regions—such as obstacles or pedestrians in autonomous driving—with greater precision, ensuring downstream tasks like navigation remain robust. With over 69 combined citations in just two years, Zheng’s contributions are rapidly shaping the future of efficient, intelligent 3D data handling, making them a key figure in advancing next-generation visual computing systems.