{"id":"https://openalex.org/W4402916297","doi":"https://doi.org/10.1109/cvprw63382.2024.00746","title":"LatentMan : Generating Consistent Animated Characters using Image Diffusion Models","display_name":"LatentMan : Generating Consistent Animated Characters using Image Diffusion Models","publication_year":2024,"publication_date":"2024-06-17","ids":{"openalex":"https://openalex.org/W4402916297","doi":"https://doi.org/10.1109/cvprw63382.2024.00746"},"language":"en","primary_location":{"id":"doi:10.1109/cvprw63382.2024.00746","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cvprw63382.2024.00746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","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/A5033942292","display_name":"Abdelrahman Eldesokey","orcid":"https://orcid.org/0000-0003-3292-7153"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Abdelrahman Eldesokey","raw_affiliation_strings":["KAUST,Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"KAUST,Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059559749","display_name":"Peter Wonka","orcid":null},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Peter Wonka","raw_affiliation_strings":["KAUST,Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"KAUST,Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033942292"],"corresponding_institution_ids":["https://openalex.org/I71920554"],"apc_list":null,"apc_paid":null,"fwci":0.3488,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59422788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"1","issue":null,"first_page":"7510","last_page":"7519"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9663000106811523,"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":0.9663000106811523,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7143887877464294},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6472707986831665},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5891121625900269},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5517046451568604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49152716994285583},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.45272305607795715},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.058561235666275024}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7143887877464294},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6472707986831665},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5891121625900269},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5517046451568604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49152716994285583},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45272305607795715},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.058561235666275024},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvprw63382.2024.00746","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cvprw63382.2024.00746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2222512263","https://openalex.org/W2471768434","https://openalex.org/W2963876278","https://openalex.org/W3204588463","https://openalex.org/W4312635677","https://openalex.org/W4312933868","https://openalex.org/W4327811131","https://openalex.org/W4385489997","https://openalex.org/W4386065764","https://openalex.org/W4386065848","https://openalex.org/W4386071957","https://openalex.org/W4386076280","https://openalex.org/W4389539288","https://openalex.org/W4390872414","https://openalex.org/W4390872556","https://openalex.org/W4390873054","https://openalex.org/W4390873135","https://openalex.org/W4390873195","https://openalex.org/W4390874580","https://openalex.org/W4393148505","https://openalex.org/W4393148714","https://openalex.org/W4402704510","https://openalex.org/W4402727782","https://openalex.org/W6600983433","https://openalex.org/W6783713337","https://openalex.org/W6809885388","https://openalex.org/W6810940779","https://openalex.org/W6838639034","https://openalex.org/W6844223692","https://openalex.org/W6844305113","https://openalex.org/W6845281891","https://openalex.org/W6846007759","https://openalex.org/W6854944684","https://openalex.org/W6858340613","https://openalex.org/W6858865347"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"We":[0,53],"propose":[1,110],"a":[2,119],"zero-shot":[3,42,132],"approach":[4,129],"for":[5],"generating":[6,136],"consistent":[7,48],"videos":[8,49,137],"of":[9,104,138,143],"animated":[10,139],"characters":[11,34,140],"based":[12],"on":[13],"Text-to-Image":[14],"(T2I)":[15],"diffusion":[16,68,116],"models.":[17],"Existing":[18],"Text-to-Video":[19],"(T2V)":[20],"methods":[21],"are":[22],"expensive":[23],"to":[24,31,45,55,70,75,100,113],"train":[25],"and":[26,35,59,146],"require":[27],"large-scale":[28],"video":[29,106],"datasets":[30],"produce":[32,46],"diverse":[33,72],"motions.":[36],"At":[37],"the":[38,77,82,87,102,105,115],"same":[39],"time,":[40],"their":[41],"alternatives":[43],"fail":[44],"temporally":[47],"with":[50],"continuous":[51,73],"motion.":[52],"strive":[54],"bridge":[56],"this":[57],"gap,":[58],"we":[60,85,98,109],"introduce":[61,86],"LATENTMAN":[62],"that":[63,92,97,121],"leverages":[64],"existing":[65,131],"text-based":[66],"motion":[67],"models":[69],"generate":[71],"motions":[74],"guide":[76],"T2I":[78],"model.":[79],"To":[80],"boost":[81],"temporal":[83],"consistency,":[84],"Spatial":[88],"Latent":[89],"Alignment":[90],"module":[91],"exploits":[93],"cross-frame":[94],"dense":[95],"correspondences":[96],"compute":[99],"align":[101],"latents":[103],"frames.":[107,126],"Furthermore,":[108],"Pixel-Wise":[111],"Guidance":[112],"steer":[114],"process":[117],"in":[118,135,141],"direction":[120],"minimizes":[122],"visual":[123],"discrepancies":[124],"between":[125],"Our":[127],"proposed":[128],"outperforms":[130],"T2V":[133],"approaches":[134],"terms":[142],"pixel-wise":[144],"consistency":[145],"user":[147],"preference.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}