{"id":"https://openalex.org/W4388189411","doi":"https://doi.org/10.1145/3581783.3612363","title":"3DStyle-Diffusion: Pursuing Fine-grained Text-driven 3D Stylization with 2D Diffusion Models","display_name":"3DStyle-Diffusion: Pursuing Fine-grained Text-driven 3D Stylization with 2D Diffusion Models","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388189411","doi":"https://doi.org/10.1145/3581783.3612363"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612363","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5066140334","display_name":"Haibo Yang","orcid":"https://orcid.org/0009-0006-6521-2145"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haibo Yang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-6521-2145","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083113249","display_name":"Yang Chen","orcid":"https://orcid.org/0009-0001-9058-5051"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Chen","raw_affiliation_strings":["University of Science and Technology of China, Heifei, China"],"raw_orcid":"https://orcid.org/0009-0001-9058-5051","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Heifei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085403640","display_name":"Yingwei Pan","orcid":"https://orcid.org/0000-0002-4344-8898"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingwei Pan","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-4344-8898","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088760097","display_name":"Ting Yao","orcid":"https://orcid.org/0000-0001-7587-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Yao","raw_affiliation_strings":["HiDream.ai Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7587-101X","affiliations":[{"raw_affiliation_string":"HiDream.ai Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080463909","display_name":"Zhineng Chen","orcid":"https://orcid.org/0000-0003-1543-6889"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhineng Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1543-6889","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101517779","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0002-5990-7307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["HiDream.ai Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5990-7307","affiliations":[{"raw_affiliation_string":"HiDream.ai Inc., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5066140334"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":9.3914,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.98316005,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6860","last_page":"6868"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.996399998664856,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.995199978351593,"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/polygon-mesh","display_name":"Polygon mesh","score":0.8190730810165405},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8165022134780884},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5705184936523438},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5332263112068176},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4894463121891022},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.46966230869293213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4345177710056305},{"id":"https://openalex.org/keywords/stylized-fact","display_name":"Stylized fact","score":0.433589369058609},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38547587394714355}],"concepts":[{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.8190730810165405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165022134780884},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5705184936523438},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5332263112068176},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4894463121891022},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.46966230869293213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4345177710056305},{"id":"https://openalex.org/C38935604","wikidata":"https://www.wikidata.org/wiki/Q4330363","display_name":"Stylized fact","level":2,"score":0.433589369058609},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38547587394714355},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612363","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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":25,"referenced_works":["https://openalex.org/W2111963422","https://openalex.org/W2798578331","https://openalex.org/W2962785568","https://openalex.org/W2963109677","https://openalex.org/W2963527086","https://openalex.org/W2964033924","https://openalex.org/W2981876524","https://openalex.org/W2982192816","https://openalex.org/W3096831136","https://openalex.org/W3109585842","https://openalex.org/W3180355996","https://openalex.org/W3183430956","https://openalex.org/W3215769467","https://openalex.org/W4294959213","https://openalex.org/W4304098884","https://openalex.org/W4312708649","https://openalex.org/W4312933868","https://openalex.org/W4313041309","https://openalex.org/W4366352791","https://openalex.org/W4386075859","https://openalex.org/W4386075992","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4390874122","https://openalex.org/W6600234944"],"related_works":["https://openalex.org/W2529311304","https://openalex.org/W4248275646","https://openalex.org/W2992609826","https://openalex.org/W3124809058","https://openalex.org/W2552900035","https://openalex.org/W2162875951","https://openalex.org/W2062875858","https://openalex.org/W4380047323","https://openalex.org/W2138330538","https://openalex.org/W2046581487"],"abstract_inverted_index":{"3D":[0,61,84,104,129,192],"content":[1],"creation":[2],"via":[3,172],"text-driven":[4],"stylization":[5,56,82,190],"has":[6],"played":[7],"a":[8,75,134,187,197],"fundamental":[9],"challenge":[10],"to":[11,34,52,140],"multimedia":[12],"and":[13,90,109,159,176,203,213,225],"graphics":[14],"community.":[15],"Recent":[16],"advances":[17],"of":[18,39,57,83,103,121,144,151,179,191,220],"cross-modal":[19,68],"foundation":[20],"models":[21],"(e.g.,":[22],"CLIP)":[23],"have":[24],"made":[25],"this":[26,71,208],"problem":[27],"feasible.":[28],"Those":[29],"approaches":[30],"commonly":[31],"leverage":[32],"CLIP":[33],"align":[35],"the":[36,43,101,142,148,204,218],"holistic":[37],"semantics":[38],"stylized":[40],"mesh":[41,105],"with":[42,86,156,162],"given":[44],"text":[45,157],"prompt.":[46],"Nevertheless,":[47],"it":[48],"is":[49,125],"not":[50],"trivial":[51],"enable":[53],"more":[54],"controllable":[55,88,136],"fine-grained":[58,81,189],"details":[59],"in":[60,182],"meshes":[62,85],"solely":[63],"based":[64],"on":[65,128],"such":[66],"semantic-level":[67],"supervision.":[69],"In":[70],"work,":[72],"we":[73,216],"propose":[74],"new":[76,198],"3DStyle-Diffusion":[77,98,132],"model":[78,139],"that":[79],"triggers":[80],"additional":[87],"appearance":[89],"geometric":[91],"guidance":[92],"from":[93,201],"2D":[94,137],"Diffusion":[95,138],"models.":[96],"Technically,":[97],"first":[99],"parameterizes":[100],"texture":[102],"into":[106],"reflectance":[107],"properties":[108],"scene":[110],"lighting":[111],"using":[112],"implicit":[113,173],"MLP":[114,174],"networks.":[115],"Meanwhile,":[116],"an":[117,183],"accurate":[118],"depth":[119,163],"map":[120],"each":[122,152],"sampled":[123],"view":[124,153],"achieved":[126],"conditioned":[127],"mesh.":[130],"Then,":[131],"leverages":[133],"pre-trained":[135],"guide":[141],"learning":[143],"rendered":[145],"images,":[146],"encouraging":[147],"synthesized":[149],"image":[150,170,180],"semantically":[154],"aligned":[155],"prompt":[158],"geometrically":[160],"consistent":[161],"map.":[164],"This":[165],"way":[166],"elegantly":[167],"integrates":[168],"both":[169,211],"rendering":[171],"networks":[175],"diffusion":[177],"process":[178],"synthesis":[181],"end-to-end":[184],"fashion,":[185],"enabling":[186],"high-quality":[188],"meshes.":[193],"We":[194],"also":[195],"build":[196],"dataset":[199],"derived":[200],"Objaverse":[202],"evaluation":[205],"protocol":[206],"for":[207],"task.":[209],"Through":[210],"qualitative":[212],"quantitative":[214],"experiments,":[215],"validate":[217],"capability":[219],"our":[221],"3DStyle-Diffusion.":[222],"Source":[223],"code":[224],"data":[226],"are":[227],"available":[228],"at":[229],"https://github.com/yanghb22-fdu/3DStyle-Diffusion-Official.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}