{"id":"https://openalex.org/W4416750394","doi":"https://doi.org/10.1109/iros60139.2025.11246315","title":"PCGE: Boosting 3D Visual Grounding via Progressive Comprehension and Geometric-topology Perception Enhancement","display_name":"PCGE: Boosting 3D Visual Grounding via Progressive Comprehension and Geometric-topology Perception Enhancement","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750394","doi":"https://doi.org/10.1109/iros60139.2025.11246315"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"Zeyue Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyue Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Bio-Vision System Laboratory, Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology,Shanghai,China,200050"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Bio-Vision System Laboratory, Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology,Shanghai,China,200050","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067613982","display_name":"Xixia Xu","orcid":"https://orcid.org/0000-0001-6305-475X"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xixia Xu","raw_affiliation_strings":["Chinese Academy of Sciences,Bio-Vision System Laboratory, Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology,Shanghai,China,200050"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Bio-Vision System Laboratory, Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology,Shanghai,China,200050","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063750451","display_name":"Runze Liu","orcid":"https://orcid.org/0009-0005-3740-8311"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runze Liu","raw_affiliation_strings":["Harbin Institute of Technology,Harbin,China,150006"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Harbin,China,150006","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078385469","display_name":"Dongchen Zhu","orcid":"https://orcid.org/0000-0002-1579-3942"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongchen Zhu","raw_affiliation_strings":["Chinese Academy of Sciences,Bio-Vision System Laboratory, Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology,Shanghai,China,200050"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Bio-Vision System Laboratory, Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology,Shanghai,China,200050","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035418350","display_name":"Jiamao Li","orcid":"https://orcid.org/0000-0002-7478-4544"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamao Li","raw_affiliation_strings":["Chinese Academy of Sciences,Bio-Vision System Laboratory, Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology,Shanghai,China,200050"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Bio-Vision System Laboratory, Science and Technology on Micro-System Laboratory, Shanghai Institute of Microsystem and Information Technology,Shanghai,China,200050","institution_ids":["https://openalex.org/I4210147322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32730109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11773","last_page":"11780"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7303000092506409,"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":0.7303000092506409,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.037700001150369644,"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":0.03680000081658363,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6601999998092651},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6485999822616577},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.483599990606308},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.46650001406669617},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.4510999917984009},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4481000006198883},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.35920000076293945},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3465000092983246}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6601999998092651},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6485999822616577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5637000203132629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5446000099182129},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.4510999917984009},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3287000060081482},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3224000036716461},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3073999881744385},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2988715931","https://openalex.org/W3035548748","https://openalex.org/W3095974555","https://openalex.org/W3107521863","https://openalex.org/W3133833192","https://openalex.org/W3140398265","https://openalex.org/W3175234951","https://openalex.org/W3203663566","https://openalex.org/W3203949114","https://openalex.org/W3211462570","https://openalex.org/W4207072548","https://openalex.org/W4214684415","https://openalex.org/W4312385518","https://openalex.org/W4312749817","https://openalex.org/W4312852845","https://openalex.org/W4313162371","https://openalex.org/W4386066792","https://openalex.org/W4386075583","https://openalex.org/W4390871962","https://openalex.org/W4390872240","https://openalex.org/W4393148022","https://openalex.org/W4402754193","https://openalex.org/W4402754253","https://openalex.org/W4402778219","https://openalex.org/W4403002335","https://openalex.org/W4405785527"],"related_works":[],"abstract_inverted_index":{"The":[0,44],"3D":[1,11],"visual":[2],"grounding":[3],"task":[4,89],"aims":[5],"to":[6,31,60,100,110,128,138],"establish":[7],"correspondences":[8],"between":[9],"the":[10,88,107,112,122,140,145],"physical":[12],"world":[13],"and":[14,79,93,166,175],"textual":[15,97],"descriptions.":[16],"Despite":[17],"significant":[18],"progress":[19],"having":[20],"been":[21],"made,":[22],"it":[23],"still":[24],"suffers":[25],"from":[26],"some":[27],"challenges":[28],"that":[29],"need":[30],"be":[32],"solved.":[33],"a)":[34],"Scene-agnostic":[35],"text":[36],"reasoning":[37,119],"causes":[38],"misaligned":[39],"target":[40,113],"region":[41,114],"concentration.":[42],"b)":[43],"regional":[45],"pseudo-center":[46,130],"interferences":[47],"result":[48],"in":[49,62],"an":[50],"inaccurate":[51],"geometric":[52,63,126,141],"center.":[53],"c)":[54],"Multi-modal":[55],"features":[56],"overemphasize":[57],"semantics,":[58],"leading":[59],"degradation":[61],"topological":[64,153],"perception":[65,143],"for":[66],"size":[67,94,133,149],"regression.":[68],"To":[69],"address":[70],"these":[71],"issues,":[72],"we":[73,105,135],"creatively":[74],"propose":[75,106,136],"a":[76,117],"Progressive":[77],"Comprehension":[78],"Geometric-topology":[80],"Perception":[81],"Enhancement":[82],"(PCGE)":[83],"one-stage":[84],"framework,":[85],"which":[86],"decouples":[87],"into":[90],"keypoint":[91,103],"estimation":[92],"regression":[95,150],"under":[96],"constraints.":[98],"Specifically,":[99],"enable":[101],"coarse-to-fine":[102],"estimation,":[104],"STAR":[108],"module":[109,124],"focus":[111],"approximately":[115],"with":[116,156,168],"scene-specific":[118],"mechanism,":[120],"while":[121],"K2C":[123],"performs":[125],"calibration":[127],"alleviate":[129],"bias.":[131],"For":[132],"regression,":[134],"GTE":[137],"enhance":[139],"boundary":[142],"during":[144],"decoding":[146],"process,":[147],"improving":[148],"via":[151],"establishing":[152],"matrices.":[154],"Compared":[155],"previous":[157],"methods,":[158],"our":[159],"approach":[160],"achieves":[161],"state-of-the-art":[162],"performance":[163],"on":[164,173,178],"ScanRefer":[165],"Sr3D,":[167],"3.94%":[169],"leads":[170,177],"of":[171],"Acc@0.50":[172],"ScanRefer,":[174],"3.7%":[176],"Sr3D.":[179]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}