{"id":"https://openalex.org/W4417433152","doi":"https://doi.org/10.48550/arxiv.2507.14841","title":"Towards Geometric and Textural Consistency 3D Scene Generation via Single Image-guided Model Generation and Layout Optimization","display_name":"Towards Geometric and Textural Consistency 3D Scene Generation via Single Image-guided Model Generation and Layout Optimization","publication_year":2025,"publication_date":"2025-07-20","ids":{"openalex":"https://openalex.org/W4417433152","doi":"https://doi.org/10.48550/arxiv.2507.14841"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.14841","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14841","pdf_url":"https://arxiv.org/pdf/2507.14841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.14841","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103239383","display_name":"Xu Tang","orcid":"https://orcid.org/0000-0002-7420-4781","observed_orcids":["https://orcid.org/0000-0002-7420-4781"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086485092","display_name":"Ruotong Li","orcid":"https://orcid.org/0000-0002-0882-8510","observed_orcids":["https://orcid.org/0000-0002-0882-8510"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ruotong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079412089","display_name":"Xiaopeng Fan","orcid":"https://orcid.org/0000-0002-9660-3636","observed_orcids":["https://orcid.org/0000-0002-9660-3636","https://orcid.org/0000-0003-4633-6629"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Xiaopeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9970999956130981,"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":0.9970999956130981,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0010999999940395355,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.0006000000284984708,"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/3d-scene-generation","display_name":"3D scene generation","score":0.9279999732971191},{"id":"https://openalex.org/keywords/geometric-consistency","display_name":"geometric consistency","score":0.7020000219345093},{"id":"https://openalex.org/keywords/texture-fidelity","display_name":"texture fidelity","score":0.7089999914169312},{"id":"https://openalex.org/keywords/image-inpainting","display_name":"image inpainting","score":0.9589999914169312},{"id":"https://openalex.org/keywords/camera-parameter-estimation","display_name":"camera parameter estimation","score":0.9819999933242798},{"id":"https://openalex.org/keywords/scene-depth-estimation","display_name":"scene depth estimation","score":0.7450000047683716},{"id":"https://openalex.org/keywords/point-cloud-alignment","display_name":"point cloud alignment","score":0.6600000262260437},{"id":"https://openalex.org/keywords/chamfer-distance","display_name":"Chamfer distance","score":0.9380000233650208}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.753600001335144},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7314000129699707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6635000109672546},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.5414999723434448},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.46129998564720154},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4032999873161316},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C23379248","wikidata":"https://www.wikidata.org/wiki/Q200904","display_name":"Epipolar geometry","level":3,"score":0.38420000672340393},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C200585589","wikidata":"https://www.wikidata.org/wiki/Q752176","display_name":"Texture mapping","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.3504999876022339},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C126057942","wikidata":"https://www.wikidata.org/wiki/Q35158","display_name":"Stereoscopy","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C84824328","wikidata":"https://www.wikidata.org/wiki/Q4633097","display_name":"2D to 3D conversion","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C32990609","wikidata":"https://www.wikidata.org/wiki/Q306542","display_name":"Transformation geometry","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.2515999972820282}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2507.14841","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14841","pdf_url":"https://arxiv.org/pdf/2507.14841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.2507.14841","doi":"https://doi.org/10.48550/arxiv.2507.14841","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.14841","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.14841","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.14841","pdf_url":"https://arxiv.org/pdf/2507.14841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"3D":[3,16,55,103,139,163,176,215],"generation":[4,36,57,70,100],"has":[5,219],"made":[6],"great":[7],"strides":[8],"in":[9,41,93,142,162,204,222],"both":[10,34],"academia":[11],"and":[12,38,62,71,83,123,146,153,164,209],"industry.":[13],"However,":[14],"generating":[15],"scenes":[17],"from":[18],"a":[19,24,50,129],"single":[20,67],"RGB":[21],"image":[22,80,114,192],"remains":[23],"significant":[25,220],"challenge,":[26],"as":[27],"current":[28],"approaches":[29],"often":[30],"struggle":[31],"to":[32,133,172],"ensure":[33,134],"object":[35],"quality":[37],"scene":[39,56,124,177,191,223],"coherence":[40],"multi-object":[42,190],"scenarios.":[43],"To":[44],"overcome":[45],"these":[46],"limitations,":[47],"we":[48],"propose":[49],"novel":[51],"three-stage":[52],"framework":[53],"for":[54,119],"with":[58,78,183],"explicit":[59,175],"geometric":[60,207],"representations":[61],"high-quality":[63],"textural":[64],"details":[65,89],"via":[66],"image-guided":[68],"model":[69,130,151],"spatial":[72,110],"layout":[73,170,224],"optimization.":[74],"Our":[75],"method":[76],"begins":[77],"an":[79,174],"instance":[81],"segmentation":[82],"inpainting":[84],"phase,":[85],"which":[86],"recovers":[87],"missing":[88],"of":[90,101,112,155,206,212],"occluded":[91],"objects":[92],"the":[94,109,138,143,147,156],"input":[95,184],"images,":[96],"thereby":[97],"achieving":[98],"complete":[99],"foreground":[102],"assets.":[104],"Subsequently,":[105],"our":[106,167,197],"approach":[107,168,198],"captures":[108],"geometry":[111],"reference":[113],"by":[115],"constructing":[116],"pseudo-stereo":[117],"viewpoint":[118],"camera":[120],"parameter":[121],"estimation":[122],"depth":[125],"inference,":[126],"while":[127],"employing":[128],"selection":[131],"strategy":[132],"optimal":[135],"alignment":[136,182],"between":[137,159],"assets":[140],"generated":[141,214],"previous":[144],"step":[145],"input.":[148],"Finally,":[149],"through":[150],"parameterization":[152],"minimization":[154],"Chamfer":[157],"distance":[158],"point":[160],"clouds":[161],"2D":[165],"space,":[166],"optimizes":[169],"parameters":[171],"produce":[173],"representation":[178],"that":[179,196],"maintains":[180],"precise":[181],"guidance":[185],"image.":[186],"Extensive":[187],"experiments":[188],"on":[189],"sets":[193],"have":[194],"demonstrated":[195],"not":[199],"only":[200],"outperforms":[201],"state-of-the-art":[202],"methods":[203],"terms":[205],"accuracy":[208],"texture":[210],"fidelity":[211],"individual":[213],"models,":[216],"but":[217],"also":[218],"advantages":[221],"synthesis.":[225]},"counts_by_year":[],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2025-10-10T00:00:00"}