{"id":"https://openalex.org/W4416052929","doi":"https://doi.org/10.1109/iccv51701.2025.00780","title":"NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors","display_name":"NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416052929","doi":"https://doi.org/10.1109/iccv51701.2025.00780"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.11427","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023140183","display_name":"Yanrui Bin","orcid":"https://orcid.org/0000-0003-2845-3928"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yanrui Bin","raw_affiliation_strings":["Spatial Intelligence Group The Hong Kong Polytechnic University,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spatial Intelligence Group The Hong Kong Polytechnic University,Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001992062","display_name":"Wenbo Hu","orcid":"https://orcid.org/0000-0001-6082-4966"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Hu","raw_affiliation_strings":["ARC Lab Tencent PCG,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab Tencent PCG,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101988620","display_name":"Haoyuan Wang","orcid":"https://orcid.org/0009-0009-1265-7572"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Haoyuan Wang","raw_affiliation_strings":["City University of Hong Kong,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Hong Kong,Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102912838","display_name":"Xinya Chen","orcid":"https://orcid.org/0000-0002-6537-4316"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinya Chen","raw_affiliation_strings":["Huazhong University of Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology,China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010963037","display_name":"Bing Wang","orcid":"https://orcid.org/0000-0003-0977-0426"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bing Wang","raw_affiliation_strings":["Spatial Intelligence Group The Hong Kong Polytechnic University,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spatial Intelligence Group The Hong Kong Polytechnic University,Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29127546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8330","last_page":"8339"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.772599995136261,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.772599995136261,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.029899999499320984,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.023099999874830246,"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/prior-probability","display_name":"Prior probability","score":0.7226999998092651},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6674000024795532},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5633999705314636},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4772999882698059},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4672999978065491},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4537000060081482},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.44119998812675476},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4075999855995178},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.3447999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293999791145325},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7226999998092651},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6674000024795532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6338000297546387},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5633999705314636},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4772999882698059},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4620000123977661},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32280001044273376},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C2985909886","wikidata":"https://www.wikidata.org/wiki/Q193147","display_name":"Spatial coherence","level":3,"score":0.2606000006198883},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2515999972820282},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25130000710487366},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.11427","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.11427","pdf_url":"https://arxiv.org/pdf/2504.11427","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.11427","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.11427","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.11427","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.11427","pdf_url":"https://arxiv.org/pdf/2504.11427","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416052929.pdf","grobid_xml":"https://content.openalex.org/works/W4416052929.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Surface":[0],"normal":[1,29,60,129],"estimation":[2,30,61],"serves":[3],"as":[4],"a":[5,8,32,92,122],"cornerstone":[6],"for":[7],"spectrum":[9],"of":[10,36,53,86,118],"computer":[11],"vision":[12],"applications.":[13],"While":[14],"numerous":[15],"efforts":[16],"have":[17],"been":[18],"devoted":[19],"to":[20,47,80,104],"static":[21],"image":[22],"scenarios,":[23],"ensuring":[24],"temporal":[25,42,51,111],"coherence":[26],"in":[27,125],"video-based":[28],"remains":[31],"formidable":[33],"challenge.":[34],"Instead":[35],"merely":[37],"augmenting":[38],"existing":[39],"methods":[40],"with":[41,74,131],"components,":[43],"we":[44,64,90],"present":[45],"NormalCrafter":[46],"leverage":[48],"the":[49,78,83,87,116],"inherent":[50],"priors":[52],"video":[54],"diffusion":[55,72],"models.":[56],"To":[57],"secure":[58],"high-fidelity":[59],"across":[62],"sequences,":[63],"propose":[65],"Semantic":[66],"Feature":[67],"Regularization":[68],"(SFR),":[69],"which":[70],"aligns":[71],"features":[73],"semantic":[75],"cues,":[76],"encouraging":[77],"model":[79],"concentrate":[81],"on":[82],"intrinsic":[84],"semantics":[85],"scene.":[88],"Moreover,":[89],"introduce":[91],"two-stage":[93],"training":[94],"protocol":[95],"that":[96],"leverages":[97],"both":[98],"latent":[99],"and":[100],"pixel":[101],"space":[102],"learning":[103],"preserve":[105],"spatial":[106],"accuracy":[107],"while":[108],"maintaining":[109],"long":[110],"context.":[112],"Extensive":[113],"evaluations":[114],"demonstrate":[115],"efficacy":[117],"our":[119],"method,":[120],"showcasing":[121],"superior":[123],"performance":[124],"generating":[126],"temporally":[127],"consistent":[128],"sequences":[130],"intricate":[132],"details":[133],"from":[134],"diverse":[135],"videos.":[136]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}