{"id":"https://openalex.org/W4415540339","doi":"https://doi.org/10.1145/3746027.3755151","title":"Stereo-GS: Multi-View Stereo Vision Model for Generalizable 3D Gaussian Splatting Reconstruction","display_name":"Stereo-GS: Multi-View Stereo Vision Model for Generalizable 3D Gaussian Splatting Reconstruction","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540339","doi":"https://doi.org/10.1145/3746027.3755151"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755151","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755151","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755151","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068213966","display_name":"Xiufeng Huang","orcid":"https://orcid.org/0009-0003-2249-3264"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiufeng Huang","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0003-2249-3264","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084054549","display_name":"Ka Chun Cheung","orcid":"https://orcid.org/0000-0002-2939-4686"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ka Chun Cheung","raw_affiliation_strings":["NVIDIA AI Technology Center, NVIDIA, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-2939-4686","affiliations":[{"raw_affiliation_string":"NVIDIA AI Technology Center, NVIDIA, Hong Kong, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091558139","display_name":"Runmin Cong","orcid":"https://orcid.org/0000-0003-0972-4008"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runmin Cong","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-0972-4008","affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077539496","display_name":"Simon See","orcid":"https://orcid.org/0000-0002-4958-9237"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon See","raw_affiliation_strings":["NVIDIA AI Technology Center, NVIDIA, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4958-9237","affiliations":[{"raw_affiliation_string":"NVIDIA AI Technology Center, NVIDIA, Singapore, Singapore","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085201191","display_name":"Renjie Wan","orcid":"https://orcid.org/0000-0002-0161-0367"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Renjie Wan","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-0161-0367","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Hong Kong, China","institution_ids":["https://openalex.org/I141568987"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9822","last_page":"9831"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9986000061035156,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9986000061035156,"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9973000288009644,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"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/robustness","display_name":"Robustness (evolution)","score":0.7192000150680542},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.6568999886512756},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4884999990463257},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48820000886917114},{"id":"https://openalex.org/keywords/gaussian-network-model","display_name":"Gaussian network model","score":0.4505999982357025},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.41609999537467957},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.3855000138282776},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.3343000113964081},{"id":"https://openalex.org/keywords/stereopsis","display_name":"Stereopsis","score":0.32519999146461487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720000147819519},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7192000150680542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6787999868392944},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.6568999886512756},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6198999881744385},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4884999990463257},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C166550679","wikidata":"https://www.wikidata.org/wiki/Q263400","display_name":"Gaussian network model","level":3,"score":0.4505999982357025},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.41609999537467957},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C65892221","wikidata":"https://www.wikidata.org/wiki/Q1113935","display_name":"Gaussian filter","level":3,"score":0.30869999527931213},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C81692654","wikidata":"https://www.wikidata.org/wiki/Q225926","display_name":"Kriging","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C7218915","wikidata":"https://www.wikidata.org/wiki/Q1054475","display_name":"Gaussian function","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C44365914","wikidata":"https://www.wikidata.org/wiki/Q17120636","display_name":"Photometric stereo","level":3,"score":0.2565999925136566},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755151","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755151","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755151","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755151","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1914386590","display_name":null,"funder_award_id":"62471278","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4811629003","display_name":null,"funder_award_id":"tsqn202306079","funder_id":"https://openalex.org/F4320326189","funder_display_name":"Taishan Scholar Project of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326189","display_name":"Taishan Scholar Project of Shandong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2973014570","https://openalex.org/W4200150166","https://openalex.org/W4285102264","https://openalex.org/W4385259380"],"related_works":[],"abstract_inverted_index":{"Generalizable":[0],"3D":[1,32,60,128,151],"Gaussian":[2,33,61,86,95],"Splatting":[3],"reconstruction":[4],"showcases":[5],"advanced":[6],"Image-to-3D":[7],"content":[8,152],"creation":[9],"but":[10],"requires":[11],"substantial":[12],"computational":[13],"resources":[14],"and":[15,35,43,76,85,94,132],"large":[16],"datasets,":[17],"posing":[18],"challenges":[19],"to":[20,102],"training":[21],"models":[22],"from":[23,67],"scratch.":[24],"Current":[25],"methods":[26,118],"usually":[27],"entangle":[28],"the":[29,104],"prediction":[30,87],"of":[31],"geometry":[34,93],"appearance,":[36,98],"which":[37],"rely":[38],"heavily":[39],"on":[40,121],"data-driven":[41],"priors":[42],"result":[44],"in":[45],"slow":[46],"regression":[47],"speeds.":[48],"To":[49],"address":[50],"this,":[51],"we":[52],"propose":[53],"Stereo-GS,":[54],"a":[55,72],"disentangled":[56],"framework":[57],"for":[58,92,97,113,149],"efficient":[59],"prediction.":[62],"Our":[63],"method":[64],"extracts":[65],"features":[66,96],"local":[68],"image":[69],"pairs":[70],"using":[71],"stereo":[73],"vision":[74],"backbone":[75],"fuses":[77],"them":[78],"via":[79],"global":[80],"attention":[81],"blocks.":[82],"Dedicated":[83],"point":[84],"heads":[88],"generate":[89],"multi-view":[90],"point-maps":[91],"combined":[99],"as":[100],"GS-maps":[101],"represent":[103],"3DGS":[105],"object.":[106],"A":[107],"refinement":[108],"network":[109],"enhances":[110],"these":[111],"GSmaps":[112],"high-quality":[114,140],"reconstruction.":[115],"Unlike":[116],"existing":[117],"that":[119],"depend":[120],"camera":[122],"parameters,":[123],"our":[124],"approach":[125],"achieves":[126],"pose-free":[127],"reconstruction,":[129],"improving":[130],"robustness":[131],"practicality.":[133],"By":[134],"reducing":[135],"resource":[136],"demands":[137],"while":[138],"maintaining":[139],"outputs,":[141],"Stereo-":[142],"GS":[143],"provides":[144],"an":[145],"efficient,":[146],"scalable":[147],"solution":[148],"real-world":[150],"generation.":[153],"Project":[154],"page:":[155],"https://kevinhuangxf.github.io/stereo-gs.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-25T00:00:00"}