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

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 ne...

Full description

Saved in:
Bibliographic Details
Main Authors: Daniele Mari, Andre F. R. Guarda, Nuno M. M. Rodrigues, Simone Milani, Fernando Pereira
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11037781/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850078802633293824
author Daniele Mari
Andre F. R. Guarda
Nuno M. M. Rodrigues
Simone Milani
Fernando Pereira
author_facet Daniele Mari
Andre F. R. Guarda
Nuno M. M. Rodrigues
Simone Milani
Fernando Pereira
author_sort Daniele Mari
collection DOAJ
description 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.
format Article
id doaj-art-4e868bb80b8e44c39b09d04c0ee797c3
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-4e868bb80b8e44c39b09d04c0ee797c32025-08-20T02:45:28ZengIEEEIEEE Access2169-35362025-01-011310802510804210.1109/ACCESS.2025.358068011037781Point Cloud Geometry Scalable Coding Using a Resolution and Quality-Conditioned Latents Probability EstimatorDaniele Mari0https://orcid.org/0000-0003-0727-3725Andre F. R. Guarda1https://orcid.org/0000-0001-5996-1074Nuno M. M. Rodrigues2https://orcid.org/0000-0001-9536-1017Simone Milani3https://orcid.org/0000-0001-8266-5839Fernando Pereira4https://orcid.org/0000-0001-6100-947XDepartment of Information Engineering, University of Padova, Padua, ItalyInstituto de Telecomunicações, Lisbon, PortugalInstituto de Telecomunicações, Lisbon, PortugalDepartment of Information Engineering, University of Padova, Padua, ItalyInstituto de Telecomunicações, Lisbon, PortugalIn 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.https://ieeexplore.ieee.org/document/11037781/Point cloud geometry codingJPEG Pleno PCCdeep learning-based codecscalable coding
spellingShingle Daniele Mari
Andre F. R. Guarda
Nuno M. M. Rodrigues
Simone Milani
Fernando Pereira
Point Cloud Geometry Scalable Coding Using a Resolution and Quality-Conditioned Latents Probability Estimator
IEEE Access
Point cloud geometry coding
JPEG Pleno PCC
deep learning-based codec
scalable coding
title Point Cloud Geometry Scalable Coding Using a Resolution and Quality-Conditioned Latents Probability Estimator
title_full Point Cloud Geometry Scalable Coding Using a Resolution and Quality-Conditioned Latents Probability Estimator
title_fullStr Point Cloud Geometry Scalable Coding Using a Resolution and Quality-Conditioned Latents Probability Estimator
title_full_unstemmed Point Cloud Geometry Scalable Coding Using a Resolution and Quality-Conditioned Latents Probability Estimator
title_short Point Cloud Geometry Scalable Coding Using a Resolution and Quality-Conditioned Latents Probability Estimator
title_sort point cloud geometry scalable coding using a resolution and quality conditioned latents probability estimator
topic Point cloud geometry coding
JPEG Pleno PCC
deep learning-based codec
scalable coding
url https://ieeexplore.ieee.org/document/11037781/
work_keys_str_mv AT danielemari pointcloudgeometryscalablecodingusingaresolutionandqualityconditionedlatentsprobabilityestimator
AT andrefrguarda pointcloudgeometryscalablecodingusingaresolutionandqualityconditionedlatentsprobabilityestimator
AT nunommrodrigues pointcloudgeometryscalablecodingusingaresolutionandqualityconditionedlatentsprobabilityestimator
AT simonemilani pointcloudgeometryscalablecodingusingaresolutionandqualityconditionedlatentsprobabilityestimator
AT fernandopereira pointcloudgeometryscalablecodingusingaresolutionandqualityconditionedlatentsprobabilityestimator