{"id":"https://openalex.org/W4412596306","doi":"https://doi.org/10.1145/3721238.3730752","title":"Splat4D: Diffusion-Enhanced 4D Gaussian Splatting for Temporally and Spatially Consistent Content Creation","display_name":"Splat4D: Diffusion-Enhanced 4D Gaussian Splatting for Temporally and Spatially Consistent Content Creation","publication_year":2025,"publication_date":"2025-07-23","ids":{"openalex":"https://openalex.org/W4412596306","doi":"https://doi.org/10.1145/3721238.3730752"},"language":"en","primary_location":{"id":"doi:10.1145/3721238.3730752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3721238.3730752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","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":null,"display_name":"Minghao Yin","orcid":"https://orcid.org/0009-0001-4252-2179"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Minghao Yin","raw_affiliation_strings":["University of Hong Kong, HongKong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0001-4252-2179","affiliations":[{"raw_affiliation_string":"University of Hong Kong, HongKong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035147532","display_name":"Yukang Cao","orcid":"https://orcid.org/0009-0001-0125-0015"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yukang Cao","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0001-0125-0015","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104001613","display_name":"Songyou Peng","orcid":"https://orcid.org/0009-0007-6085-8059"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Songyou Peng","raw_affiliation_strings":["Google DeepMind, San Francisco, USA"],"raw_orcid":"https://orcid.org/0009-0007-6085-8059","affiliations":[{"raw_affiliation_string":"Google DeepMind, San Francisco, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056485902","display_name":"Kai Han","orcid":"https://orcid.org/0000-0002-7995-9999"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Han","raw_affiliation_strings":["University of Hong Kong, HongKong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0002-7995-9999","affiliations":[{"raw_affiliation_string":"University of Hong Kong, HongKong, Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30683123,"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":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9994000196456909,"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":0.9987000226974487,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9983000159263611,"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":0.6967004537582397},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5785648822784424},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.512395441532135},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.50738924741745},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.37162065505981445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32022809982299805},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12198492884635925},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09254556894302368}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6967004537582397},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5785648822784424},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.512395441532135},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.50738924741745},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.37162065505981445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32022809982299805},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12198492884635925},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09254556894302368},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3721238.3730752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3721238.3730752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/201676","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/201676","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2105649179","https://openalex.org/W2741137940","https://openalex.org/W2990138404","https://openalex.org/W3035551320","https://openalex.org/W4200150166","https://openalex.org/W4221151978","https://openalex.org/W4385318467","https://openalex.org/W4386065887","https://openalex.org/W4386071957","https://openalex.org/W4386075660","https://openalex.org/W4386076215","https://openalex.org/W4390871705","https://openalex.org/W4390873331","https://openalex.org/W4390873542","https://openalex.org/W4390874424","https://openalex.org/W4390874575","https://openalex.org/W4402716105","https://openalex.org/W4402722906","https://openalex.org/W4402727236","https://openalex.org/W4402727792","https://openalex.org/W4402727821","https://openalex.org/W4402727912","https://openalex.org/W4402753842","https://openalex.org/W4402780257","https://openalex.org/W6600822972","https://openalex.org/W6624719054"],"related_works":["https://openalex.org/W4250539519","https://openalex.org/W4294018197","https://openalex.org/W4233433299","https://openalex.org/W2379384513","https://openalex.org/W2213288308","https://openalex.org/W2884856691","https://openalex.org/W4244821991","https://openalex.org/W2125732910","https://openalex.org/W2909905999","https://openalex.org/W2317264789"],"abstract_inverted_index":{"Generating":[0],"high-quality":[1],"4D":[2,41,107,109],"content":[3,42,114],"from":[4,44],"monocular":[5,46],"videos\u2014for":[6],"applications":[7,102],"such":[8,103],"as":[9,104],"digital":[10],"humans":[11],"and":[12,18,24,67,112],"AR/VR\u2014poses":[13],"challenges":[14],"in":[15,100],"ensuring":[16],"temporal":[17],"spatial":[19],"consistency,":[20],"preserving":[21],"intricate":[22],"details,":[23],"incorporating":[25],"user":[26,120],"guidance":[27],"effectively.":[28],"To":[29],"overcome":[30],"these":[31],"challenges,":[32],"we":[33],"introduce":[34],"Splat4D,":[35],"a":[36,45,63],"novel":[37],"framework":[38],"enabling":[39],"high-fidelity":[40],"generation":[43],"video.":[47],"Splat4D":[48,79,97],"achieves":[49],"superior":[50],"performance":[51,83],"while":[52],"maintaining":[53],"faithful":[54],"spatial-temporal":[55],"coherence,":[56],"by":[57],"leveraging":[58],"multi-view":[59],"rendering,":[60],"inconsistency":[61],"identification,":[62],"video":[64],"diffusion":[65],"model,":[66],"an":[68],"asymmetric":[69],"U-Net":[70],"for":[71],"refinement.":[72],"Through":[73],"extensive":[74],"evaluations":[75],"on":[76],"public":[77],"benchmarks,":[78],"consistently":[80],"demonstrates":[81],"state-of-the-art":[82],"across":[84],"various":[85,101],"metrics,":[86],"underscoring":[87],"the":[88,94],"efficacy":[89],"of":[90,96],"our":[91],"approach.":[92],"Additionally,":[93],"versatility":[95],"is":[98],"validated":[99],"text/image":[105],"conditioned":[106],"generation,":[108,111],"human":[110],"text-guided":[113],"editing,":[115],"producing":[116],"coherent":[117],"outcomes":[118],"following":[119],"instructions.":[121],"Project":[122],"page:":[123],"https://visual-ai.github.io/splat4d":[124]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}