Point Cloud Compression and Objective Quality Assessment: A Survey

2025-06-28

AI Summary

To address technical bottlenecks in 3D point cloud compression and quality assessment for autonomous driving, robotics, and immersive applications, this paper systematically surveys recent advances in both handcrafted and deep learning–based methods. We propose a hybrid compression framework integrating geometric coding with deep feature learning, supporting multimodal inputs and enhancing high-level semantic representation. Additionally, we adopt objective quality metrics—including PCQM—and conduct unified benchmarking on emerging point cloud datasets. Experimental evaluation comprehensively compares state-of-the-art algorithms across rate-distortion performance, visual fidelity, and inference latency. Results reveal the superiority of learning-based methods under high compression ratios, while confirming the irreplaceable real-time efficiency of traditional approaches. Our work establishes a new paradigm for perception-oriented, efficient point cloud coding and trustworthy quality assessment, substantiated by empirical evidence. (149 words)

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Data Compression

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

The rapid growth of 3D point cloud data, driven by applications in autonomous driving, robotics, and immersive environments, has led to criticals demand for efficient compression and quality assessment techniques. Unlike traditional 2D media, point clouds present unique challenges due to their irregular structure, high data volume, and complex attributes. This paper provides a comprehensive survey of recent advances in point cloud compression (PCC) and point cloud quality assessment (PCQA), emphasizing their significance for real-time and perceptually relevant applications. We analyze a wide range of handcrafted and learning-based PCC algorithms, along with objective PCQA metrics. By benchmarking representative methods on emerging datasets, we offer detailed comparisons and practical insights into their strengths and limitations. Despite notable progress, challenges such as enhancing visual fidelity, reducing latency, and supporting multimodal data remain. This survey outlines future directions, including hybrid compression frameworks and advanced feature extraction strategies, to enable more efficient, immersive, and intelligent 3D applications.

Problem

• Efficient compression for large 3D point cloud data
• Objective quality assessment of point cloud attributes
• Addressing irregular structure challenges in point clouds

Innovation

• Survey of point cloud compression and quality assessment
• Analysis of handcrafted and learning-based PCC algorithms
• Benchmarking methods on emerging datasets for insights