{"id":"https://openalex.org/W4416040044","doi":"https://doi.org/10.1109/wacv61042.2026.00130","title":"PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models","display_name":"PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416040044","doi":"https://doi.org/10.1109/wacv61042.2026.00130"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.10529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109725543","display_name":"Zilu Guo","orcid":"https://orcid.org/0009-0000-9011-1756"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilu Guo","raw_affiliation_strings":["FNii-Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FNii-Shenzhen","institution_ids":["https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630591","display_name":"Hongbin Lin","orcid":"https://orcid.org/0000-0002-5269-3393"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbin Lin","raw_affiliation_strings":["FNii-Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FNii-Shenzhen","institution_ids":["https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114832227","display_name":"Zhihao Yuan","orcid":"https://orcid.org/0000-0003-3100-1252"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Yuan","raw_affiliation_strings":["FNii-Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FNii-Shenzhen","institution_ids":["https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015757467","display_name":"Chaoda Zheng","orcid":"https://orcid.org/0000-0001-9347-4181"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoda Zheng","raw_affiliation_strings":["FNii-Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FNii-Shenzhen","institution_ids":["https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104263666","display_name":"Pengshuo Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pengshuo Qiu","raw_affiliation_strings":["CUHK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102634569","display_name":"Dongzhi Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dongzhi Jiang","raw_affiliation_strings":["CUHK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078082000","display_name":"Renrui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Renrui Zhang","raw_affiliation_strings":["CUHK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049444898","display_name":"Chun-Mei Feng","orcid":"https://orcid.org/0000-0002-3025-8964"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Chun-Mei Feng","raw_affiliation_strings":["University College Dublin,Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College Dublin,Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100332644","display_name":"Zhen Li","orcid":"https://orcid.org/0000-0002-9783-169X"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhen Li","raw_affiliation_strings":["CUHK-Shenzhen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUHK-Shenzhen","institution_ids":["https://openalex.org/I4210116924","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1273","last_page":"1283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6065999865531921,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6065999865531921,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.09480000287294388,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.09139999747276306,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5095999836921692},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5066999793052673},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5019000172615051},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5011000037193298},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.4878000020980835},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4747999906539917},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44209998846054077},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.42010000348091125},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4162999987602234},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.40700000524520874}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134999871253967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5134000182151794},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5066999793052673},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5019000172615051},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4823000133037567},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4747999906539917},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4162999987602234},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.37940001487731934},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.35420000553131104},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.10529","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10529","pdf_url":"https://arxiv.org/pdf/2503.10529","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.10529","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.10529","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.10529","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.10529","pdf_url":"https://arxiv.org/pdf/2503.10529","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311778","display_name":"China Association for Science and Technology","ror":"https://ror.org/035vmht26"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,26,39,66,73,99,129,139,165,184],"Multimodal":[1],"Large":[2],"Language":[3],"Models":[4],"(MLLMs)":[5],"have":[6],"recently":[7],"made":[8],"substantial":[9],"advancements.":[10],"However,":[11],"their":[12],"potential":[13],"remains":[14],"untapped,":[15],"primarily":[16],"due":[17],"to":[18,31,37,125],"the":[19,117],"limited":[20],"quantity":[21],"and":[22,46,98,119,147,173,187,199],"suboptimal":[23],"quality":[24],"of":[25,79,109,196],"datasets.":[27],"Current":[28],"approaches":[29],"attempt":[30],"transfer":[32],"knowledge":[33],"from":[34,101],"2D":[35,85,97],"MLLMs":[36,74,86],"expand":[38],"instruction":[40,61],"data,":[41],"but":[42],"still":[43],"face":[44],"modality":[45],"domain":[47],"gaps.":[48],"To":[49,155],"this":[50,121,157],"end,":[51],"we":[52,134,159],"introduce":[53,161],"PiSA-Engine":[54,104],"(Point-Self-Augmented-Engine),":[55],"a":[56,76,106,163],"new":[57],"framework":[58,124],"for":[59,82],"generating":[60],"point-language":[62],"datasets":[63],"enriched":[64],"with":[65,171],"spatial":[67],"semantics.":[68],"We":[69,113],"observe":[70],"that":[71],"existing":[72],"offer":[75],"comprehensive":[77,164],"understanding":[78],"point":[80],"clouds":[81],"annotation,":[83],"while":[84],"excel":[87],"at":[88],"cross-validation":[89],"by":[90],"providing":[91],"complementary":[92],"information.":[93],"By":[94],"integrating":[95],"holistic":[96],"insights":[100],"off-the-shelf":[102],"MLLMs,":[103],"enables":[105],"continuous":[107],"cycle":[108],"high-quality":[110],"data":[111],"generation.":[112],"select":[114],"PointLLM":[115],"as":[116],"baseline":[118],"adopt":[120],"co-evolution":[122],"training":[123],"develop":[126],"an":[127],"enhanced":[128],"MLLM,":[130],"termed":[131],"PointLLM-PiSA.":[132],"Additionally,":[133],"identify":[135],"limitations":[136],"in":[137,152,182],"previous":[138],"benchmarks,":[140],"which":[141],"often":[142],"feature":[143],"coarse":[144],"language":[145],"captions":[146],"insufficient":[148],"category":[149],"diversity,":[150],"resulting":[151],"inaccurate":[153],"evaluations.":[154],"address":[156],"gap,":[158],"further":[160],"PiSA-Bench,":[162,192],"benchmark":[166],"covering":[167],"six":[168],"key":[169],"aspects":[170],"detailed":[172],"diverse":[174],"labels.":[175],"Experimental":[176],"results":[177],"demonstrate":[178],"PointLLM-PiSA\u2019s":[179],"state-of-the-art":[180],"performance":[181],"zero-shot":[183],"object":[185],"captioning":[186],"generative":[188],"classification":[189],"on":[190],"our":[191],"achieving":[193],"significant":[194],"improvements":[195],"46.45%":[197],"(+8.33%)":[198],"63.75%":[200],"(+16.25%),":[201],"respectively.":[202],"Project":[203],"page:":[204],"CG-ops/PiSA.":[205]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}