{"id":"https://openalex.org/W4408352528","doi":"https://doi.org/10.1109/icassp49660.2025.10887623","title":"OrientDream: Streamlining Text-to-3D Generation with Explicit Orientation Control","display_name":"OrientDream: Streamlining Text-to-3D Generation with Explicit Orientation Control","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352528","doi":"https://doi.org/10.1109/icassp49660.2025.10887623"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5063312909","display_name":"Yuzhong Huang","orcid":"https://orcid.org/0000-0001-6705-8694"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuzhong Huang","raw_affiliation_strings":["University of Southern California,Information Science Institute,Los Angeles,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Information Science Institute,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002709735","display_name":"Fred Morstatter","orcid":"https://orcid.org/0000-0002-0247-4328"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fred Morstatter","raw_affiliation_strings":["University of Southern California,Information Science Institute,Los Angeles,USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Information Science Institute,Los Angeles,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5063312909"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05636515,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9980000257492065,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9980000257492065,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.972599983215332,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9603000283241272,"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/computer-science","display_name":"Computer science","score":0.6594229340553284},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.6264788508415222},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.500279426574707},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34605491161346436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2984009385108948},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11502096056938171},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.11234498023986816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6594229340553284},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.6264788508415222},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.500279426574707},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34605491161346436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2984009385108948},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11502096056938171},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.11234498023986816}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887623","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":12,"referenced_works":["https://openalex.org/W2962785568","https://openalex.org/W3034600949","https://openalex.org/W4221151978","https://openalex.org/W4312933868","https://openalex.org/W4386065402","https://openalex.org/W4386065411","https://openalex.org/W4386065887","https://openalex.org/W4386075859","https://openalex.org/W4386075992","https://openalex.org/W4386083144","https://openalex.org/W4388979610","https://openalex.org/W4390873331"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"In":[0],"the":[1,30],"evolving":[2],"landscape":[3],"of":[4,91],"text-to-3D":[5],"technology,":[6],"Dreamfusion":[7],"[9]":[8],"optimizes":[9],"implicit":[10,92],"representations":[11],"like":[12],"NeRF":[13,107],"using":[14],"Score":[15],"Distillation":[16],"Sampling":[17],"(SDS)":[18],"but":[19,113],"faces":[20,29],"limitations":[21],"in":[22],"both":[23],"fidelity":[24],"and":[25,34,72],"speed.":[26],"Specifically,":[27],"it":[28],"multi-head":[31],"Janus":[32],"issue":[33],"exhibits":[35],"a":[36,44,63,83],"relatively":[37],"slow":[38],"optimization":[39,95,117],"process.":[40],"We":[41],"present":[42],"OrientDream,":[43],"camera":[45,69],"orientation":[46,70],"conditioned":[47],"framework":[48],"for":[49,88],"efficient,":[50],"multi-view":[51,111],"consistent":[52,110],"3D":[53],"generation":[54],"from":[55,75],"text":[56],"prompts.":[57],"OrientDream":[58],"achieves":[59,115],"this":[60],"by":[61,126],"pre-training":[62],"2D":[64],"text-to-image":[65],"diffusion":[66],"module":[67],"with":[68,109],"features":[71],"utilizing":[73],"data":[74],"MVImgNet.":[76],"To":[77],"shorten":[78],"training":[79],"time,":[80],"we":[81],"introduced":[82],"decoupled":[84],"back-propagation":[85],"technique,":[86],"allowing":[87],"multiple":[89],"updates":[90],"parameters":[93],"per":[94],"cycle.":[96],"Our":[97],"experiments":[98],"reveal":[99],"that":[100],"our":[101],"method":[102],"not":[103],"only":[104],"produces":[105],"high-quality":[106],"models":[108],"properties":[112],"also":[114],"an":[116],"speed":[118],"significantly":[119],"greater":[120],"than":[121],"existing":[122],"methods,":[123],"as":[124],"quantified":[125],"comparative":[127],"metrics.":[128]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
