{"id":"https://openalex.org/W7105693793","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228786","title":"MSIA-SDiT3D: 3D Multi-Scale Interpolation Attention in Lightweight Diffusion Transformers for 3D Point Cloud Generation","display_name":"MSIA-SDiT3D: 3D Multi-Scale Interpolation Attention in Lightweight Diffusion Transformers for 3D Point Cloud Generation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105693793","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228786"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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":null,"display_name":"Xiaobao He","orcid":null},"institutions":[{"id":"https://openalex.org/I50632499","display_name":"Chongqing University of Technology","ror":"https://ror.org/04vgbd477","country_code":"CN","type":"education","lineage":["https://openalex.org/I50632499"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaobao He","raw_affiliation_strings":["Chongqing University of Technology,College of Computer Science and Engineering,China"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Technology,College of Computer Science and Engineering,China","institution_ids":["https://openalex.org/I50632499"]}]},{"author_position":"last","author":{"id":null,"display_name":"Dan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145825","display_name":"China Academy Of Machinery Science & Technology (China)","ror":"https://ror.org/04gpxrn68","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210145825"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Huang","raw_affiliation_strings":["Chongqing University of Technology,China Research & Development Academy of Machinery Equipment,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Technology,China Research & Development Academy of Machinery Equipment,Beijing,China","institution_ids":["https://openalex.org/I4210145825"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I50632499"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57416254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9376999735832214,"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":0.9376999735832214,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.01759999990463257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.005100000184029341,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer 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":0.8526999950408936},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5073999762535095},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.44369998574256897},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3878999948501587},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.3781999945640564},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.33799999952316284},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3343000113964081}],"concepts":[{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.8526999950408936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6916000247001648},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5073999762535095},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48240000009536743},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.44369998574256897},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3878999948501587},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.33489999175071716},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3343000113964081},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3172000050544739},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28540000319480896},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.25220000743865967},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2796426482","https://openalex.org/W2850910281","https://openalex.org/W2963046274","https://openalex.org/W2985683375","https://openalex.org/W2986615800","https://openalex.org/W3017336954","https://openalex.org/W3045146419","https://openalex.org/W3111535274","https://openalex.org/W3116564952","https://openalex.org/W3141954417","https://openalex.org/W3166584442","https://openalex.org/W3171030514","https://openalex.org/W3180196270","https://openalex.org/W3212887756","https://openalex.org/W4214755140","https://openalex.org/W4312910764","https://openalex.org/W4365130488","https://openalex.org/W4386071957","https://openalex.org/W4386986709","https://openalex.org/W4390872297","https://openalex.org/W4396982183","https://openalex.org/W4402753635","https://openalex.org/W4402753750","https://openalex.org/W4402816868"],"related_works":[],"abstract_inverted_index":{"Recently,":[0],"diffusion":[1,148],"Transformers":[2,149],"have":[3,18],"demonstrated":[4],"strong":[5],"potential":[6],"in":[7,11,38,74,126,147,237],"generative":[8,21],"tasks,":[9],"especially":[10],"2D":[12],"image":[13],"generation,":[14,154],"where":[15],"DiT":[16],"models":[17,236],"shown":[19],"excellent":[20],"results.":[22],"The":[23],"DiT-3D":[24,58],"model,":[25,199,255],"which":[26,117,155,202],"inherits":[27],"the":[28,47,67,71,79,85,96,99,103,110,114,119,122,177,188,206,252,258,265,279],"design":[29,192],"principles":[30],"of":[31,70,98,109,121,128,159,181,209,212,239,260,267,273,275],"DiT,":[32],"has":[33],"likewise":[34],"achieved":[35],"state-of-the-art":[36,246],"performance":[37,120],"3D":[39,54,61,141,151,195,220],"point":[40,56,75,111,124,152,182,196,221],"cloud":[41,76,112,125,153,183,197],"generation":[42,198,241,280],"tasks.":[43],"However,":[44],"due":[45],"to":[46,65,95,101,217],"enormous":[48],"computational":[49,68,189,225],"overhead":[50],"associated":[51],"with":[52,215,223,251],"high-resolution":[53],"voxel":[55],"clouds,":[57],"introduces":[59],"a":[60,140,193],"window":[62,80],"attention":[63,81,166],"mechanism":[64,73,82],"reduce":[66,187],"cost":[69],"self-attention":[72],"generation.":[77,184],"Although":[78],"significantly":[83],"reduces":[84,257],"training":[86],"time":[87],"and":[88,106,131,170,172,179,243,264],"memory":[89],"usage,":[90],"its":[91],"localization":[92],"limitation":[93],"leads":[94],"difficulty":[97],"model":[100],"capture":[102],"global":[104],"layout":[105],"local":[107],"details":[108],"at":[113,167],"same":[115],"time,":[116],"affects":[118],"generated":[123],"terms":[127,238],"shape":[129],"complexity":[130],"detail":[132],"retention.":[133],"To":[134,185],"address":[135],"this":[136],"problem,":[137],"we":[138,191],"propose":[139],"Multi-Scale":[142],"Interpolated":[143],"Attention":[144],"Mechanism":[145],"(3D-MSIA)":[146],"for":[150],"achieves":[156],"efficient":[157],"modeling":[158],"multi-scale":[160],"geometrical":[161],"structures":[162],"by":[163,262],"independently":[164],"calculating":[165],"multiple":[168],"scales":[169],"interpolating":[171],"fusing":[173],"them,":[174],"thus":[175],"improving":[176],"quality":[178,242],"diversity":[180],"further":[186],"cost,":[190],"lightweight":[194],"namely":[200],"MSIA-SDiT3D,":[201],"is":[203,270],"based":[204],"on":[205],"minimum":[207],"number":[208,259],"parameters":[210,261],"version":[211],"DiT-3D-S":[213],"combined":[214],"3D-MSIA,":[216],"generate":[218],"high-fidelity":[219],"clouds":[222],"low":[224],"resources.":[226],"Experimental":[227],"results":[228],"show":[229],"that":[230,274],"our":[231],"method":[232],"outperforms":[233],"existing":[234],"baseline":[235],"both":[240],"diversity,":[244],"achieving":[245],"performance.":[247],"In":[248],"particular,":[249],"compared":[250],"best-performing":[253],"DiT-3D-XL":[254,276],"MSIA-SDiT3D":[256],"93%,":[263],"amount":[266],"FLOPs":[268],"computation":[269],"only":[271],"1/7th":[272],"while":[277],"guaranteeing":[278],"quality.":[281]},"counts_by_year":[],"updated_date":"2025-11-15T23:13:30.683059","created_date":"2025-11-14T00:00:00"}