{"id":"https://openalex.org/W4405032425","doi":"https://doi.org/10.48550/arxiv.2412.00100","title":"Steering Rectified Flow Models in the Vector Field for Controlled Image Generation","display_name":"Steering Rectified Flow Models in the Vector Field for Controlled Image Generation","publication_year":2024,"publication_date":"2024-11-27","ids":{"openalex":"https://openalex.org/W4405032425","doi":"https://doi.org/10.48550/arxiv.2412.00100"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2412.00100","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.00100","pdf_url":"https://arxiv.org/pdf/2412.00100","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.00100","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018555559","display_name":"Maitreya Patel","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patel, Maitreya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104307325","display_name":"Wen Song","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109600054","display_name":"Dimitris Metaxas","orcid":"https://orcid.org/0000-0002-6033-282X","observed_orcids":["https://orcid.org/0000-0002-6033-282X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Metaxas, Dimitris N.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002278578","display_name":"Yezhou Yang","orcid":"https://orcid.org/0000-0003-0126-8976","observed_orcids":["https://orcid.org/0000-0003-0126-8976"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yezhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9994999766349792,"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":0.9994999766349792,"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/T10688","display_name":"Image and Signal Denoising Methods","score":9.999999747378752e-05,"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":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/classifier-free-guidance","display_name":"classifier-free guidance","score":0.7929999828338623},{"id":"https://openalex.org/keywords/linear-inverse-problems","display_name":"linear inverse problems","score":0.7260000109672546},{"id":"https://openalex.org/keywords/image-editing","display_name":"image editing","score":0.984000027179718},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.44200000166893005}],"concepts":[{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.570207953453064},{"id":"https://openalex.org/C91188154","wikidata":"https://www.wikidata.org/wiki/Q186247","display_name":"Vector field","level":2,"score":0.5475455522537231},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5254232883453369},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5144839286804199},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4520542323589325},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4354335069656372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34893542528152466},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3106711208820343},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.13342642784118652},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.07030516862869263}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2412.00100","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.00100","pdf_url":"https://arxiv.org/pdf/2412.00100","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.00100","doi":"https://doi.org/10.48550/arxiv.2412.00100","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.00100","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.00100","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.00100","pdf_url":"https://arxiv.org/pdf/2412.00100","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2592405099","https://openalex.org/W2938786841","https://openalex.org/W2012002054","https://openalex.org/W2783536463","https://openalex.org/W2041424614","https://openalex.org/W2888156545","https://openalex.org/W2011117899","https://openalex.org/W2755342338","https://openalex.org/W3036909545","https://openalex.org/W2003404947"],"abstract_inverted_index":{"Diffusion":[0],"models":[1,23],"(DMs)":[2],"excel":[3],"in":[4,77,93,170],"photorealism,":[5],"image":[6,17,117,131,146],"editing,":[7],"and":[8,16,44,56,67,96,145,163,175],"solving":[9],"inverse":[10,143],"problems,":[11,144],"aided":[12],"by":[13,121],"classifier-free":[14],"guidance":[15],"inversion":[18,57],"techniques.":[19],"However,":[20],"rectified":[21],"flow":[22],"(RFMs)":[24],"remain":[25],"underexplored":[26],"for":[27,115,129,134,151],"these":[28],"tasks.":[29],"Existing":[30],"DM-based":[31],"methods":[32],"often":[33],"require":[34],"additional":[35],"training,":[36,153],"lack":[37],"generalization":[38],"to":[39,50,110],"pretrained":[40],"latent":[41],"models,":[42],"underperform,":[43],"demand":[45],"significant":[46],"computational":[47],"resources":[48],"due":[49],"extensive":[51,161],"backpropagation":[52],"through":[53],"ODE":[54],"solvers":[55],"processes.":[58],"In":[59],"this":[60,100],"work,":[61],"we":[62,87,102,159],"first":[63,136],"develop":[64],"a":[65,94,126],"theoretical":[66],"empirical":[68],"understanding":[69],"of":[70,75,172],"the":[71,80,90,107,112,135,149],"vector":[72,91,108],"field":[73,92,109],"dynamics":[74],"RFMs":[76],"efficiently":[78],"guiding":[79],"denoising":[81,113],"trajectory.":[82],"Our":[83],"findings":[84],"reveal":[85],"that":[86,165],"can":[88],"navigate":[89],"deterministic":[95],"gradient-free":[97],"manner.":[98],"Utilizing":[99],"property,":[101],"propose":[103],"FlowChef,":[104],"which":[105],"leverages":[106],"steer":[111],"trajectory":[114],"controlled":[116,130],"generation":[118,132],"tasks,":[119],"facilitated":[120],"gradient":[122],"skipping.":[123],"FlowChef":[124,166],"is":[125],"unified":[127],"framework":[128],"that,":[133],"time,":[137],"simultaneously":[138],"addresses":[139],"classifier":[140],"guidance,":[141],"linear":[142],"editing":[147],"without":[148],"need":[150],"extra":[152],"inversion,":[154],"or":[155],"intensive":[156],"backpropagation.":[157],"Finally,":[158],"perform":[160],"evaluations":[162],"show":[164],"significantly":[167],"outperforms":[168],"baselines":[169],"terms":[171],"performance,":[173],"memory,":[174],"time":[176],"requirements,":[177],"achieving":[178],"new":[179],"state-of-the-art":[180],"results.":[181],"Project":[182],"Page:":[183],"\\url{https://flowchef.github.io}.":[184]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2024-12-05T00:00:00"}