{"id":"https://openalex.org/W4415540472","doi":"https://doi.org/10.1145/3746027.3754743","title":"Unknown Pixel Mask Based Fine-tuning of 2D Inpainting Models for Unbounded 3D Scene Generation from a Single Image","display_name":"Unknown Pixel Mask Based Fine-tuning of 2D Inpainting Models for Unbounded 3D Scene Generation from a Single Image","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540472","doi":"https://doi.org/10.1145/3746027.3754743"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754743","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754743","pdf_url":null,"source":null,"license":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011595741","display_name":"Dezhi Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezhi Zheng","raw_affiliation_strings":["School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0003-8683-3635","affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109635081","display_name":"K F Deng","orcid":"https://orcid.org/0009-0009-1352-2952"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaijun Deng","raw_affiliation_strings":["School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0009-1352-2952","affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033865377","display_name":"Xianxu Hou","orcid":"https://orcid.org/0000-0002-8728-2842"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianxu Hou","raw_affiliation_strings":["School of AI and Advanced Computing, Xi'an Jiaotong-Liverpool University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8728-2842","affiliations":[{"raw_affiliation_string":"School of AI and Advanced Computing, Xi'an Jiaotong-Liverpool University, Suzhou, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101698854","display_name":"Jinbao Wang","orcid":"https://orcid.org/0000-0001-5916-8965"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"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":"Jinbao Wang","raw_affiliation_strings":["Computer Vision Institute, School of Artificial Intelligence, Shenzhen University, Shenzhen, China and Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5916-8965","affiliations":[{"raw_affiliation_string":"Computer Vision Institute, School of Artificial Intelligence, Shenzhen University, Shenzhen, China and Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403894","display_name":"Xiaoqin Wang","orcid":"https://orcid.org/0000-0002-6813-7666"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqin Wang","raw_affiliation_strings":["School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6813-7666","affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019313200","display_name":"Linlin Shen","orcid":"https://orcid.org/0000-0003-1420-0815"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"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":"Linlin Shen","raw_affiliation_strings":["Computer Vision Institute, School of Artificial Intelligence, Shenzhen University, Shenzhen, China and Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1420-0815","affiliations":[{"raw_affiliation_string":"Computer Vision Institute, School of Artificial Intelligence, Shenzhen University, Shenzhen, China and Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I3131625388"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":"9306","last_page":"9315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9990000128746033,"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/inpainting","display_name":"Inpainting","score":0.9567999839782715},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.728600025177002},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5629000067710876},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5357999801635742},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.5027999877929688},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.49470001459121704},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.3508000075817108},{"id":"https://openalex.org/keywords/point-cloud","display_name":"Point cloud","score":0.3465999960899353}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.9567999839782715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7950999736785889},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7452999949455261},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.728600025177002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7249000072479248},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5629000067710876},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5357999801635742},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.5027999877929688},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.49470001459121704},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C200873422","wikidata":"https://www.wikidata.org/wiki/Q5448821","display_name":"Filling-in","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.2786000072956085},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C2992444157","wikidata":"https://www.wikidata.org/wiki/Q775079","display_name":"Single point","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.26669999957084656},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754743","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754743","pdf_url":null,"source":null,"license":null,"license_id":null,"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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5515857334","display_name":null,"funder_award_id":"62206180,82261138629,62320106007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5889964250","display_name":null,"funder_award_id":"2024YFF0618403","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8442882701","display_name":null,"funder_award_id":"JCYJ20220531101412030","funder_id":"https://openalex.org/F4320329174","funder_display_name":"Shenzhen Municipal Science and Technology Innovation Council"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329174","display_name":"Shenzhen Municipal Science and Technology Innovation Council","ror":"https://ror.org/017n8df75"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2085905957","https://openalex.org/W2962785568","https://openalex.org/W2981721547","https://openalex.org/W3111114371","https://openalex.org/W3196466825","https://openalex.org/W3199003182","https://openalex.org/W3215769467","https://openalex.org/W3216352822","https://openalex.org/W4312286719","https://openalex.org/W4312315996","https://openalex.org/W4312933868","https://openalex.org/W4385318467","https://openalex.org/W4386075660","https://openalex.org/W4386075859","https://openalex.org/W4386083144","https://openalex.org/W4386083151","https://openalex.org/W4387596111","https://openalex.org/W4390873054","https://openalex.org/W4390873331","https://openalex.org/W4394597526"],"related_works":[],"abstract_inverted_index":{"Conventional":[0],"2D":[1,10,59,77],"inpainting":[2,78,113],"models":[3,79,114],"are":[4,127],"trained":[5],"using":[6],"masks":[7,57,82],"confined":[8],"to":[9,18,46,54,83,96],"scenarios,":[11],"resulting":[12],"in":[13,38,149],"meaningless":[14],"content":[15],"when":[16],"applied":[17],"3D-specific":[19,22],"masks.":[20],"These":[21],"masks,":[23,28],"termed":[24],"Unknown":[25],"Pixels":[26],"(UP)":[27],"represent":[29],"unseen":[30],"pixels":[31],"from":[32,63,101,121],"novel":[33,93],"viewpoints":[34],"that":[35,115,143],"remain":[36],"obscured":[37],"the":[39,72,132],"original":[40,133],"input":[41],"image.":[42],"Existing":[43],"methods":[44,148],"attempt":[45],"mitigate":[47],"this":[48,88],"issue":[49],"by":[50,106],"employing":[51],"post-processing":[52],"techniques":[53],"transform":[55],"UP":[56,81],"into":[58,131],"equivalents,":[60],"frequently":[61],"suffering":[62],"unnatural":[64],"distortions.":[65,86],"To":[66],"address":[67],"these":[68],"issues,":[69],"we":[70,90],"investigate":[71],"efficacy":[73],"of":[74],"directly":[75],"training":[76],"with":[80],"circumvent":[84],"such":[85],"In":[87],"paper,":[89],"introduce":[91],"a":[92,102],"framework":[94,145],"designed":[95],"generate":[97],"unbounded":[98],"3D":[99],"scenes":[100],"single":[103],"image,":[104],"guided":[105],"textual":[107],"descriptions.":[108],"Our":[109],"approach":[110],"leverages":[111],"fine-tuned":[112],"iteratively":[116],"reconstruct":[117],"incomplete":[118],"images":[119],"originating":[120],"pure":[122],"projection.":[123],"The":[124],"generated":[125],"points":[126],"then":[128],"seamlessly":[129],"integrated":[130],"point":[134],"cloud":[135],"via":[136],"pixel-wise":[137],"depth":[138],"alignment.":[139],"Extensive":[140],"evaluations":[141],"demonstrate":[142],"our":[144],"outperforms":[146],"existing":[147],"scene":[150],"quality,":[151],"processing":[152],"speed,":[153],"and":[154],"memory":[155],"efficiency.":[156]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}