{"id":"https://openalex.org/W4415482458","doi":"https://doi.org/10.1109/tcsvt.2025.3624688","title":"Learned Point Cloud Attribute Compression With Cross-Scale Point Transformer and Geometry-Aware Context Prediction Entropy Model","display_name":"Learned Point Cloud Attribute Compression With Cross-Scale Point Transformer and Geometry-Aware Context Prediction Entropy Model","publication_year":2025,"publication_date":"2025-10-23","ids":{"openalex":"https://openalex.org/W4415482458","doi":"https://doi.org/10.1109/tcsvt.2025.3624688"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3624688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3624688","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102804376","display_name":"Xiao Huo","orcid":"https://orcid.org/0000-0003-0287-5196"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Huo","raw_affiliation_strings":["School of Telecommunication Engineering, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-0287-5196","affiliations":[{"raw_affiliation_string":"School of Telecommunication Engineering, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041968797","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0001-7291-8193"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["School of Telecommunication Engineering, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0001-7291-8193","affiliations":[{"raw_affiliation_string":"School of Telecommunication Engineering, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055433813","display_name":"Fuzheng Yang","orcid":"https://orcid.org/0000-0002-8369-8015"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuzheng Yang","raw_affiliation_strings":["School of Telecommunication Engineering, Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-8369-8015","affiliations":[{"raw_affiliation_string":"School of Telecommunication Engineering, Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2113731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"4","first_page":"5538","last_page":"5552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9020000100135803,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.6848999857902527},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5317999720573425},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.4429999887943268},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.424699991941452},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.3878999948501587},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3781999945640564},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.36149999499320984},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.35269999504089355},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.3522999882698059},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.3361999988555908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.763700008392334},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.6848999857902527},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5317999720573425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46639999747276306},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43939998745918274},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.424699991941452},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.3361999988555908},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3190999925136566},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C1769480","wikidata":"https://www.wikidata.org/wiki/Q1345239","display_name":"Entropy encoding","level":3,"score":0.30889999866485596},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C153338461","wikidata":"https://www.wikidata.org/wiki/Q2651","display_name":"Arithmetic coding","level":4,"score":0.28610000014305115},{"id":"https://openalex.org/C169805256","wikidata":"https://www.wikidata.org/wiki/Q1361381","display_name":"Transform coding","level":4,"score":0.28610000014305115},{"id":"https://openalex.org/C48983235","wikidata":"https://www.wikidata.org/wiki/Q593161","display_name":"Light field","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C2778045648","wikidata":"https://www.wikidata.org/wiki/Q176827","display_name":"Markov random field","level":4,"score":0.2768999934196472},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.25519999861717224},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3624688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3624688","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8290150096","display_name":null,"funder_award_id":"62371358","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1986678681","https://openalex.org/W1995875735","https://openalex.org/W2194775991","https://openalex.org/W2227290239","https://openalex.org/W2319503556","https://openalex.org/W2415653907","https://openalex.org/W2594519801","https://openalex.org/W2769157872","https://openalex.org/W2941750291","https://openalex.org/W2963125977","https://openalex.org/W2996973935","https://openalex.org/W3021906059","https://openalex.org/W3034469748","https://openalex.org/W3044110181","https://openalex.org/W3081203363","https://openalex.org/W3091766805","https://openalex.org/W3096387236","https://openalex.org/W3131427579","https://openalex.org/W3134748538","https://openalex.org/W3170603795","https://openalex.org/W3185759054","https://openalex.org/W4297685253","https://openalex.org/W4307104049","https://openalex.org/W4310591442","https://openalex.org/W4311415873","https://openalex.org/W4312806968","https://openalex.org/W4317794929","https://openalex.org/W4372260571","https://openalex.org/W4385765627","https://openalex.org/W4385815536","https://openalex.org/W4388018819","https://openalex.org/W4388543857","https://openalex.org/W4392309256","https://openalex.org/W4392909893","https://openalex.org/W4402557597","https://openalex.org/W4402571450","https://openalex.org/W4402835130","https://openalex.org/W4403331526","https://openalex.org/W4410536665"],"related_works":[],"abstract_inverted_index":{"Point":[0],"clouds":[1,22],"are":[2,23,52],"a":[3,55,72,129,172,209],"fundamental":[4],"format":[5],"for":[6,12,179],"immersive":[7],"experiences,":[8],"posing":[9],"significant":[10,37],"challenges":[11],"storage":[13],"and":[14,25,59,80,98,103,120,143,167,170,194,201,218,224],"transmission.":[15],"Unlike":[16,146],"2D":[17],"image":[18],"compression,":[19],"3D":[20],"point":[21,40,49,74],"sparse":[24,32,92],"irregular,":[26],"complicating":[27],"their":[28],"attribute":[29,42],"compression.":[30],"While":[31],"convolution-based":[33],"methods":[34,148],"have":[35],"made":[36],"success":[38],"on":[39,95],"cloud":[41],"compression":[43],"by":[44,54,138,176],"leveraging":[45],"the":[46,89,104,117,141,155,186,190,214,219],"sparsity":[47,101],"of":[48,91,154],"clouds,":[50],"they":[51],"constrained":[53],"limited":[56],"receptive":[57,118],"field":[58,119],"insufficient":[60],"adaptability":[61],"to":[62,77,111,122,213],"diverse":[63],"inputs.":[64,124],"To":[65],"overcome":[66],"these":[67],"limitations,":[68],"this":[69],"paper":[70],"proposes":[71],"novel":[73],"transformer-based":[75],"architecture":[76],"exploit":[78],"correlations":[79],"aggregate":[81],"features":[82,160],"across":[83,164],"multiple":[84],"scales":[85,110],"(CSFormer).":[86],"It":[87,207],"retains":[88],"advantage":[90],"convolution":[93],"operating":[94],"occupied":[96],"voxels":[97],"leverages":[99],"varied":[100],"distributions":[102],"geometry":[105,178],"distortions":[106],"inherent":[107],"in":[108,203],"consecutive":[109],"construct":[112],"attention":[113],"maps,":[114],"effectively":[115],"extending":[116],"adapting":[121],"different":[123],"We":[125],"further":[126],"introduced":[127],"GCPEM,":[128],"Geometry-aware":[130],"Context":[131],"Prediction-based":[132],"Entropy":[133],"Model":[134],"that":[135,149,185],"reduces":[136],"bitrates":[137],"jointly":[139],"utilizing":[140],"spatial":[142],"channel":[144,168],"dependencies.":[145],"previous":[147],"capture":[150],"only":[151],"one":[152],"type":[153],"information,":[156],"GCPEM":[157],"organizes":[158],"latent":[159],"into":[161],"groups":[162],"interlaced":[163],"both":[165],"space":[166],"dimensions":[169],"employs":[171],"context-prediction":[173],"mechanism":[174],"guided":[175],"known":[177],"efficient":[180],"coding.":[181],"Experimental":[182],"results":[183],"show":[184],"proposed":[187],"method":[188,193,217],"outperforms":[189],"state-of-the-art":[191,215],"learning-based":[192,216],"MPEG":[195],"standard":[196],"G-PCC":[197],"codec":[198],"over":[199],"7%":[200],"28%":[202],"BD-BR":[204],"(Y-PSNR),":[205],"respectively.":[206],"has":[208],"time":[210],"complexity":[211],"comparable":[212],"G-PCC.":[220],"The":[221],"source":[222],"code":[223],"trained":[225],"models":[226],"will":[227],"be":[228],"released":[229],"at":[230],"https://github.com/X-H-offical/CST-PCAC-plus.git.":[231]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-23T00:00:00"}