{"id":"https://openalex.org/W7169260307","doi":"https://doi.org/10.1145/3799902.3811169","title":"BoxCtrl: 3D-Aware Visual Prompting for Geometric Image Editing","display_name":"BoxCtrl: 3D-Aware Visual Prompting for Geometric Image Editing","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7169260307","doi":"https://doi.org/10.1145/3799902.3811169"},"language":null,"primary_location":{"id":"doi:10.1145/3799902.3811169","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811169","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3799902.3811169","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029787563","display_name":"Fang Wang","orcid":"https://orcid.org/0000-0002-3327-4177"},"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":"Feifei Wang","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-5611-3886","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007476607","display_name":"Shiyuan Yang","orcid":"https://orcid.org/0000-0001-8213-5803"},"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":"Shiyuan Yang","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-8213-5803","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449177","display_name":"Xiaoyu Li","orcid":"https://orcid.org/0000-0003-2588-1687"},"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":"Xiaoyu Li","raw_affiliation_strings":["Tencent, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2588-1687","affiliations":[{"raw_affiliation_string":"Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013972536","display_name":"Jing Liao","orcid":"https://orcid.org/0000-0001-7014-5377"},"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":"Jing Liao","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-7014-5377","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6714000105857849},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5149999856948853},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4115000069141388},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4104999899864197},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.37950000166893005},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.3700999915599823},{"id":"https://openalex.org/keywords/geometric-modeling","display_name":"Geometric modeling","score":0.3693000078201294},{"id":"https://openalex.org/keywords/visual-learning","display_name":"Visual learning","score":0.3684000074863434},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.3549000024795532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7448999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7117999792098999},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6714000105857849},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5485000014305115},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4104999899864197},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.3549000024795532},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C181095308","wikidata":"https://www.wikidata.org/wiki/Q1541599","display_name":"Geometric primitive","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C200756006","wikidata":"https://www.wikidata.org/wiki/Q336092","display_name":"Visual angle","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3799902.3811169","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811169","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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"}],"best_oa_location":{"id":"doi:10.1145/3799902.3811169","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811169","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2133665775","https://openalex.org/W2962785568","https://openalex.org/W3159481202","https://openalex.org/W4285102264","https://openalex.org/W4312339971","https://openalex.org/W4400582405","https://openalex.org/W4402716373","https://openalex.org/W4402754115","https://openalex.org/W4402774219","https://openalex.org/W4404965672","https://openalex.org/W4409262348","https://openalex.org/W4412590239","https://openalex.org/W4412636516","https://openalex.org/W4413146762","https://openalex.org/W4413156007","https://openalex.org/W4413156031","https://openalex.org/W4415796838","https://openalex.org/W4417125485","https://openalex.org/W7133194112","https://openalex.org/W7160048357","https://openalex.org/W7160059250","https://openalex.org/W7160103956","https://openalex.org/W7160176840","https://openalex.org/W7160185424"],"related_works":[],"abstract_inverted_index":{"As":[0],"instruction-based":[1],"editing":[2,17,166,208,275],"models":[3,8],"and":[4,25,34,84,102,107,163,247,273],"multimodal":[5],"large":[6],"language":[7],"continue":[9],"to":[10,54,114,140,155],"advance,":[11],"a":[12,40,49,77,105,156,170,194,239],"wide":[13],"range":[14],"of":[15,160,187,213],"image":[16,28],"tasks":[18],"have":[19],"become":[20],"feasible.":[21],"However,":[22,210],"achieving":[23],"precise":[24,158],"consistent":[26,142],"geometric":[27,130,161,245,255],"editing,":[29],"such":[30],"as":[31,76,125],"translating,":[32],"scaling":[33],"rotating":[35],"in":[36,118,150],"3D":[37,69],"space,":[38,153],"remains":[39],"major":[41],"challenge.":[42],"In":[43],"this":[44,56],"work,":[45],"we":[46,191,227],"introduce":[47,169],"BoxCtrl,":[48],"3D-aware":[50],"visual":[51,78,110,126,248],"prompting":[52,127],"framework":[53],"address":[55,184],"problem.":[57],"Unlike":[58],"text-only":[59],"or":[60],"coarse":[61],"2D-guided":[62],"approaches,":[63],"our":[64,250],"method":[65],"introduces":[66],"informative":[67],"RGB":[68,94],"bounding":[70,121],"boxes":[71],"projected":[72],"onto":[73],"2D":[74],"images":[75],"prompting.":[79],"Each":[80],"box":[81],"is":[82,217,279],"outlined":[83],"its":[85,99,119],"three":[86],"orthogonal":[87],"faces":[88,145],"are":[89],"individually":[90],"painted":[91],"with":[92,146,206],"different":[93],"colors,":[95],"which":[96,123,202],"simultaneously":[97],"encode":[98],"position,":[100],"size":[101],"orientation,":[103],"providing":[104],"compact":[106],"intuitive":[108],"in-context":[109],"example.":[111],"The":[112],"key":[113],"BoxCtrl\u2019s":[115],"success":[116],"lies":[117],"well-designed":[120],"boxes,":[122],"serve":[124],"that":[128,264],"decouple":[129],"control":[131],"from":[132],"appearance":[133],"control.":[134],"This":[135],"design":[136],"enables":[137],"the":[138,147,151,185,199,204,211,214,220],"model":[139,205,216],"learn":[141],"correspondences":[143],"between":[144],"same":[148],"color":[149],"latent":[152],"leading":[154],"more":[157,164],"understanding":[159],"intention":[162],"accurate":[165],"result.":[167],"We":[168],"two-stage":[171],"training":[172,189],"paradigm":[173],"comprising":[174],"Supervised":[175],"Fine-Tuning":[176],"(SFT)":[177],"followed":[178],"by":[179,219,238],"Reinforcement":[180],"Learning":[181],"(RL).":[182],"To":[183,224],"scarcity":[186],"paired":[188],"data,":[190],"first":[192],"construct":[193],"large-scale":[195],"synthetic":[196],"dataset":[197],"for":[198],"SFT":[200,215],"stage,":[201],"equips":[203],"fundamental":[207],"capabilities.":[209],"generalization":[212],"constrained":[218],"synthetic-to-real":[221],"domain":[222],"gap.":[223],"bridge":[225],"this,":[226],"incorporate":[228],"an":[229],"online":[230],"RL":[231],"stage":[232],"leveraging":[233],"unpaired":[234],"real-world":[235],"data.":[236],"Guided":[237],"comprehensive":[240],"reward":[241],"function":[242],"evaluating":[243],"both":[244],"accuracy":[246],"fidelity,":[249],"SFT-RL":[251],"strategy":[252],"significantly":[253],"enhances":[254],"precision":[256],"while":[257],"maintaining":[258],"photorealistic":[259],"quality.":[260],"Extensive":[261],"experiments":[262],"demonstrate":[263],"BoxCtrl":[265],"achieves":[266],"state-of-the-art":[267],"performance":[268],"across":[269],"translation,":[270],"rotation,":[271],"scaling,":[272],"composite":[274],"tasks.":[276],"Our":[277],"code":[278],"available":[280],"at":[281],"https://github.com/beaglew/BoxCtrl.":[282]},"counts_by_year":[],"updated_date":"2026-07-17T05:58:32.477365","created_date":"2026-07-17T00:00:00"}