Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression

Efficient point cloud compression is fundamental to enable the deployment of virtual and mixed reality applications, since the number of points to code can range in the order of millions. In this paper, we present a novel data-driven geometry compression method for static point clouds based on learn...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2019-05
Hauptverfasser: Quach, Maurice, Valenzise, Giuseppe, Dufaux, Frederic
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Quach, Maurice
Valenzise, Giuseppe
Dufaux, Frederic
description Efficient point cloud compression is fundamental to enable the deployment of virtual and mixed reality applications, since the number of points to code can range in the order of millions. In this paper, we present a novel data-driven geometry compression method for static point clouds based on learned convolutional transforms and uniform quantization. We perform joint optimization of both rate and distortion using a trade-off parameter. In addition, we cast the decoding process as a binary classification of the point cloud occupancy map. Our method outperforms the MPEG reference solution in terms of rate-distortion on the Microsoft Voxelized Upper Bodies dataset with 51.5% BDBR savings on average. Moreover, while octree-based methods face exponential diminution of the number of points at low bitrates, our method still produces high resolution outputs even at low bitrates. Code and supplementary material are available at https://github.com/mauriceqch/pcc_geo_cnn .
doi_str_mv 10.48550/arxiv.1903.08548
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_1903_08548</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2194936535</sourcerecordid><originalsourceid>FETCH-LOGICAL-a525-9b8ff4f9a5c1873f71484f3cc77ac96c67ce8a9cde295e08873eaf9f1fceab823</originalsourceid><addsrcrecordid>eNotj89LwzAAhYMgOOb-AE8GPLfmZ5McpegUCnrovWRZIh1tMpN22P_euO3y3uV7Dz4AHjAqmeQcPev4259KrBAtkeRM3oAVoRQXkhFyBzYpHRBCpBKEc7oCTWN19L3_hnXwpzDMUx-8HmAbtU8uxDHBnLAJKS3wK_R-gvUQ5j3c2jDaKS55Nx6jTSnv7sGt00Oym2uvQfv22tbvRfO5_ahfmkJzwgu1k84xpzQ3WArqBGaSOWqMENqoylTCWKmV2VuiuEUyM1Y75bAzVu8koWvweLk9q3bH2I86Lt2_cndWzsTThTjG8DPbNHWHMMfslTqCFVO04pTTP7zjWvY</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2194936535</pqid></control><display><type>article</type><title>Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression</title><source>arXiv.org</source><source>Free E- Journals</source><creator>Quach, Maurice ; Valenzise, Giuseppe ; Dufaux, Frederic</creator><creatorcontrib>Quach, Maurice ; Valenzise, Giuseppe ; Dufaux, Frederic</creatorcontrib><description>Efficient point cloud compression is fundamental to enable the deployment of virtual and mixed reality applications, since the number of points to code can range in the order of millions. In this paper, we present a novel data-driven geometry compression method for static point clouds based on learned convolutional transforms and uniform quantization. We perform joint optimization of both rate and distortion using a trade-off parameter. In addition, we cast the decoding process as a binary classification of the point cloud occupancy map. Our method outperforms the MPEG reference solution in terms of rate-distortion on the Microsoft Voxelized Upper Bodies dataset with 51.5% BDBR savings on average. Moreover, while octree-based methods face exponential diminution of the number of points at low bitrates, our method still produces high resolution outputs even at low bitrates. Code and supplementary material are available at https://github.com/mauriceqch/pcc_geo_cnn .</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.1903.08548</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning ; Data compression ; Decoding ; Distortion ; Mixed reality ; MPEG encoders ; Occupancy ; Octrees ; Optimization ; Statistics - Machine Learning ; Video compression ; Virtual reality</subject><ispartof>arXiv.org, 2019-05</ispartof><rights>2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,780,881,27902</link.rule.ids><backlink>$$Uhttps://doi.org/10.1109/ICIP.2019.8803413$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.48550/arXiv.1903.08548$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Quach, Maurice</creatorcontrib><creatorcontrib>Valenzise, Giuseppe</creatorcontrib><creatorcontrib>Dufaux, Frederic</creatorcontrib><title>Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression</title><title>arXiv.org</title><description>Efficient point cloud compression is fundamental to enable the deployment of virtual and mixed reality applications, since the number of points to code can range in the order of millions. In this paper, we present a novel data-driven geometry compression method for static point clouds based on learned convolutional transforms and uniform quantization. We perform joint optimization of both rate and distortion using a trade-off parameter. In addition, we cast the decoding process as a binary classification of the point cloud occupancy map. Our method outperforms the MPEG reference solution in terms of rate-distortion on the Microsoft Voxelized Upper Bodies dataset with 51.5% BDBR savings on average. Moreover, while octree-based methods face exponential diminution of the number of points at low bitrates, our method still produces high resolution outputs even at low bitrates. Code and supplementary material are available at https://github.com/mauriceqch/pcc_geo_cnn .</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><subject>Data compression</subject><subject>Decoding</subject><subject>Distortion</subject><subject>Mixed reality</subject><subject>MPEG encoders</subject><subject>Occupancy</subject><subject>Octrees</subject><subject>Optimization</subject><subject>Statistics - Machine Learning</subject><subject>Video compression</subject><subject>Virtual reality</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><sourceid>GOX</sourceid><recordid>eNotj89LwzAAhYMgOOb-AE8GPLfmZ5McpegUCnrovWRZIh1tMpN22P_euO3y3uV7Dz4AHjAqmeQcPev4259KrBAtkeRM3oAVoRQXkhFyBzYpHRBCpBKEc7oCTWN19L3_hnXwpzDMUx-8HmAbtU8uxDHBnLAJKS3wK_R-gvUQ5j3c2jDaKS55Nx6jTSnv7sGt00Oym2uvQfv22tbvRfO5_ahfmkJzwgu1k84xpzQ3WArqBGaSOWqMENqoylTCWKmV2VuiuEUyM1Y75bAzVu8koWvweLk9q3bH2I86Lt2_cndWzsTThTjG8DPbNHWHMMfslTqCFVO04pTTP7zjWvY</recordid><startdate>20190522</startdate><enddate>20190522</enddate><creator>Quach, Maurice</creator><creator>Valenzise, Giuseppe</creator><creator>Dufaux, Frederic</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKY</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20190522</creationdate><title>Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression</title><author>Quach, Maurice ; Valenzise, Giuseppe ; Dufaux, Frederic</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a525-9b8ff4f9a5c1873f71484f3cc77ac96c67ce8a9cde295e08873eaf9f1fceab823</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><topic>Data compression</topic><topic>Decoding</topic><topic>Distortion</topic><topic>Mixed reality</topic><topic>MPEG encoders</topic><topic>Occupancy</topic><topic>Octrees</topic><topic>Optimization</topic><topic>Statistics - Machine Learning</topic><topic>Video compression</topic><topic>Virtual reality</topic><toplevel>online_resources</toplevel><creatorcontrib>Quach, Maurice</creatorcontrib><creatorcontrib>Valenzise, Giuseppe</creatorcontrib><creatorcontrib>Dufaux, Frederic</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Computer Science</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Quach, Maurice</au><au>Valenzise, Giuseppe</au><au>Dufaux, Frederic</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression</atitle><jtitle>arXiv.org</jtitle><date>2019-05-22</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>Efficient point cloud compression is fundamental to enable the deployment of virtual and mixed reality applications, since the number of points to code can range in the order of millions. In this paper, we present a novel data-driven geometry compression method for static point clouds based on learned convolutional transforms and uniform quantization. We perform joint optimization of both rate and distortion using a trade-off parameter. In addition, we cast the decoding process as a binary classification of the point cloud occupancy map. Our method outperforms the MPEG reference solution in terms of rate-distortion on the Microsoft Voxelized Upper Bodies dataset with 51.5% BDBR savings on average. Moreover, while octree-based methods face exponential diminution of the number of points at low bitrates, our method still produces high resolution outputs even at low bitrates. Code and supplementary material are available at https://github.com/mauriceqch/pcc_geo_cnn .</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.1903.08548</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2019-05
issn 2331-8422
language eng
recordid cdi_arxiv_primary_1903_08548
source arXiv.org; Free E- Journals
subjects Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Data compression
Decoding
Distortion
Mixed reality
MPEG encoders
Occupancy
Octrees
Optimization
Statistics - Machine Learning
Video compression
Virtual reality
title Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T20%3A02%3A26IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Learning%20Convolutional%20Transforms%20for%20Lossy%20Point%20Cloud%20Geometry%20Compression&rft.jtitle=arXiv.org&rft.au=Quach,%20Maurice&rft.date=2019-05-22&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.1903.08548&rft_dat=%3Cproquest_arxiv%3E2194936535%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2194936535&rft_id=info:pmid/&rfr_iscdi=true