{"id":"https://openalex.org/W7118176926","doi":"https://doi.org/10.1109/aiccsa66935.2025.11315400","title":"Attentional Trajectory Modeling for Text-to-3D Generation with Gaussian Multi-View Diffusion and SDS++","display_name":"Attentional Trajectory Modeling for Text-to-3D Generation with Gaussian Multi-View Diffusion and SDS++","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7118176926","doi":"https://doi.org/10.1109/aiccsa66935.2025.11315400"},"language":null,"primary_location":{"id":"doi:10.1109/aiccsa66935.2025.11315400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa66935.2025.11315400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","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":"https://openalex.org/A5120403171","display_name":"Marena Anis Labib","orcid":null},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Marena Anis Labib","raw_affiliation_strings":["MSA University,Dept. of Computer Science,Giza,Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MSA University,Dept. of Computer Science,Giza,Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030894498","display_name":"Ali Hamdi","orcid":"https://orcid.org/0000-0002-2301-6588"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Ali Hamdi","raw_affiliation_strings":["MSA University,Dept. of Computer Science,Giza,Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MSA University,Dept. of Computer Science,Giza,Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121648537","display_name":"Khaled Shaban","orcid":null},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Khaled Shaban","raw_affiliation_strings":["Qatar University,Dept. of Computer Science,Doha,Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar University,Dept. of Computer Science,Doha,Qatar","institution_ids":["https://openalex.org/I60342839"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5120403171"],"corresponding_institution_ids":["https://openalex.org/I145487455"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63626839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.24289999902248383,"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":0.24289999902248383,"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/T12290","display_name":"Human Motion and Animation","score":0.20020000636577606,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.18389999866485596,"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/pixel","display_name":"Pixel","score":0.45820000767707825},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4521999955177307},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.44290000200271606},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4287000000476837},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4065999984741211},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.350600004196167},{"id":"https://openalex.org/keywords/cinematography","display_name":"Cinematography","score":0.3395000100135803},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.33629998564720154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6832000017166138},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6424000263214111},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6362000107765198},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.45820000767707825},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.35850000381469727},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.350600004196167},{"id":"https://openalex.org/C100991257","wikidata":"https://www.wikidata.org/wiki/Q590870","display_name":"Cinematography","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C2777521450","wikidata":"https://www.wikidata.org/wiki/Q43171778","display_name":"CRTS","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aiccsa66935.2025.11315400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa66935.2025.11315400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W4298187450","https://openalex.org/W4386065887","https://openalex.org/W4386075859","https://openalex.org/W4386075992","https://openalex.org/W4386083144","https://openalex.org/W4386126700","https://openalex.org/W4390873542","https://openalex.org/W4390874211","https://openalex.org/W4391256869","https://openalex.org/W4391681755","https://openalex.org/W4402263770","https://openalex.org/W4402753842","https://openalex.org/W4402775760","https://openalex.org/W4402916482","https://openalex.org/W4402952317","https://openalex.org/W4415797067"],"related_works":[],"abstract_inverted_index":{"The":[0],"advancement":[1,187],"in":[2,12,188,194],"converting":[3],"text":[4],"into":[5],"3D":[6,17,78,83,89],"scenes":[7],"has":[8],"driven":[9],"significant":[10],"improvements":[11],"generating":[13],"realistic":[14,93],"and":[15,32,71,91,100,137,142,157,179,197],"adaptable":[16],"models.":[18],"However,":[19],"existing":[20],"methods":[21],"face":[22],"persistent":[23],"challenges,":[24],"including":[25,130],"inconsistent":[26],"multi-view":[27,175],"generation,":[28,190],"limited":[29],"scene":[30,79],"complexity,":[31],"an":[33],"inability":[34],"to":[35,116],"handle":[36,117],"real-world":[37,119],"datasets":[38],"with":[39,85,127,191],"varying":[40],"camera":[41,120],"trajectories.":[42],"To":[43],"address":[44],"these":[45],"limitations,":[46],"we":[47],"introduce":[48],"a":[49,53,148,185],"novel":[50],"approach":[51,146],"utilizing":[52],"four-part":[54],"system:":[55],"the":[56],"Cinematographer":[57],"(Trajectory":[58],"Diffusion":[59,67],"Transformer":[60],"-":[61,69],"Traj-DiT),":[62],"Decorator":[63],"(Gaussian-driven":[64],"Multi-view":[65],"Latent":[66],"Model":[68],"GM-LDM,":[70],"Detailer":[72],"(SDS++":[73],"loss).":[74],"Our":[75,104,145],"model":[76],"enhances":[77],"generation":[80],"by":[81],"aligning":[82],"Gaussians":[84],"pixel":[86],"data,":[87],"refining":[88],"structures,":[90],"applying":[92],"surface":[94],"properties":[95],"while":[96],"ensuring":[97],"view-to-view":[98],"consistency":[99],"accommodating":[101],"complex":[102],"scenes.":[103],"research":[105],"methodology":[106],"integrates":[107],"dense-view":[108],"trajectories":[109],"processed":[110],"through":[111],"BERT,":[112],"employing":[113],"multi-head":[114],"selfattention":[115],"intricate,":[118],"movements.":[121],"We":[122],"conducted":[123],"extensive":[124],"experimental":[125],"comparisons":[126],"state-of-theart":[128],"models,":[129],"DreamFusion,":[131],"Magic3D,":[132],"LatentNeRF,":[133],"SJC,":[134],"Fantasia3D,":[135],"ProlificDreamer,":[136],"Director3D,":[138],"using":[139],"BRISQUE,":[140],"NIQE,":[141],"CLIP-Score":[143,158],"metrics.":[144],"achieved":[147],"BRISQUE":[149],"score":[150,154,159],"of":[151,155,160],"23.3,":[152],"NIQE":[153],"4.34,":[156],"86.1,":[161],"significantly":[162],"outperforming":[163],"all":[164],"competing":[165],"methods.":[166],"These":[167],"results":[168],"demonstrate":[169],"our":[170],"model\u2019s":[171],"superior":[172],"visual":[173],"clarity,":[174],"consistency,":[176],"geometric":[177],"accuracy,":[178],"photo-realistic":[180],"rendering.":[181],"This":[182],"work":[183],"represents":[184],"substantial":[186],"text-to-3D":[189],"promising":[192],"applications":[193],"gaming,":[195],"simulation,":[196],"virtual":[198],"reality.":[199]},"counts_by_year":[],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2026-01-05T00:00:00"}
