Point Cloud Geometry Scalable Coding Using a Resolution and Quality-conditioned Latents Probability Estimator

2025-02-19

AI Summary

This work addresses the redundancy issue in point cloud deep learning compression arising from heterogeneous multi-terminal requirements, proposing the first single-bitstream geometric coding framework supporting joint resolution and quality scalability. Methodologically, it introduces a jointly conditioned latent variable probability estimator that models statistical dependencies of latent variables across diverse rate-distortion (RD) trade-offs and multiple resolutions. It further incorporates a hyperprior-based conditional entropy model and a multi-scale latent alignment mechanism, integrated within the JPEG Pleno learned coding framework. Experiments demonstrate that the proposed method enables arbitrary-resolution and arbitrary-quality decoding from a single bitstream, with only a 0.5% BD-rate penalty and manageable computational overhead. This breakthrough reconciles the long-standing tension between scalability and coding efficiency in point cloud compression.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

In the current age, users consume multimedia content in very heterogeneous scenarios in terms of network, hardware, and display capabilities. A naive solution to this problem is to encode multiple independent streams, each covering a different possible requirement for the clients, with an obvious negative impact in both storage and computational requirements. These drawbacks can be avoided by using codecs that enable scalability, i.e., the ability to generate a progressive bitstream, containing a base layer followed by multiple enhancement layers, that allow decoding the same bitstream serving multiple reconstructions and visualization specifications. While scalable coding is a well-known and addressed feature in conventional image and video codecs, this paper focuses on a new and very different problem, notably the development of scalable coding solutions for deep learning-based Point Cloud (PC) coding. The peculiarities of this 3D representation make it hard to implement flexible solutions that do not compromise the other functionalities of the codec. This paper proposes a joint quality and resolution scalability scheme, named Scalable Resolution and Quality Hyperprior (SRQH), that, contrary to previous solutions, can model the relationship between latents obtained with models trained for different RD tradeoffs and/or at different resolutions. Experimental results obtained by integrating SRQH in the emerging JPEG Pleno learning-based PC coding standard show that SRQH allows decoding the PC at different qualities and resolutions with a single bitstream while incurring only in a limited RD penalty and increment in complexity w.r.t. non-scalable JPEG PCC that would require one bitstream per coding configuration.

Problem

• Scalable coding for Point Clouds
• Joint quality and resolution scalability
• Single bitstream for multiple decoding specifications

Innovation

• Scalable Resolution Quality Hyperprior
• Single bitstream multi-quality decoding
• JPEG Pleno integration