{"id":"https://openalex.org/W7164812590","doi":"https://doi.org/10.1145/3805622.3810678","title":"SlimNet: High-Quality and Efficient Object Removal by Eliciting Latent Capabilities of Diffusion Models","display_name":"SlimNet: High-Quality and Efficient Object Removal by Eliciting Latent Capabilities of Diffusion Models","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164812590","doi":"https://doi.org/10.1145/3805622.3810678"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810678","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810678","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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810678","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138651049","display_name":"Xiao Ma","orcid":"https://orcid.org/0009-0006-7873-2289"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Ma","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China and Lenovo Ltd, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-7873-2289","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China and Lenovo Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210156165","https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011405516","display_name":"Jin Yuan","orcid":"https://orcid.org/0000-0002-9954-0693"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Yuan","raw_affiliation_strings":["Lenovo Ltd, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9954-0693","affiliations":[{"raw_affiliation_string":"Lenovo Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446997","display_name":"Yao Zhang","orcid":"https://orcid.org/0000-0002-8759-4811"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhang","raw_affiliation_strings":["Lenovo Ltd, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8759-4811","affiliations":[{"raw_affiliation_string":"Lenovo Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101411299","display_name":"Cheng Zhong","orcid":"https://orcid.org/0000-0002-6886-7319"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Zhong","raw_affiliation_strings":["Lenovo Ltd, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6886-7319","affiliations":[{"raw_affiliation_string":"Lenovo Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101873354","display_name":"Zhongchao Shi","orcid":"https://orcid.org/0000-0002-5216-3827"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongchao Shi","raw_affiliation_strings":["Lenovo Ltd, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5216-3827","affiliations":[{"raw_affiliation_string":"Lenovo Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728569","display_name":"Jianping Fan","orcid":"https://orcid.org/0000-0003-2290-1785"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping Fan","raw_affiliation_strings":["Lenovo Ltd, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2290-1785","affiliations":[{"raw_affiliation_string":"Lenovo Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030226818","display_name":"Guihua Zeng","orcid":"https://orcid.org/0000-0001-6623-2945"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guihua Zeng","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6623-2945","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"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":"2732","last_page":"2740"},"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":0.8027999997138977,"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":0.8027999997138977,"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/T11019","display_name":"Image Enhancement Techniques","score":0.10329999774694443,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.03620000183582306,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7394000291824341},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7276999950408936},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5669000148773193},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5554999709129333},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4796000123023987},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.45080000162124634},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.3991999924182892},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.38920000195503235},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.35510000586509705}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7394000291824341},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7276999950408936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715399980545044},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5669000148773193},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5667999982833862},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5501999855041504},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4796000123023987},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.30300000309944153},{"id":"https://openalex.org/C512554520","wikidata":"https://www.wikidata.org/wiki/Q815844","display_name":"Method","level":3,"score":0.30149999260902405},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810678","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810678","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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810678","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810678","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 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1993120651","https://openalex.org/W2012875423","https://openalex.org/W2105038642","https://openalex.org/W2133665775","https://openalex.org/W2295936755","https://openalex.org/W2331128040","https://openalex.org/W2475287302","https://openalex.org/W2738588019","https://openalex.org/W2798365772","https://openalex.org/W2962785568","https://openalex.org/W2963231084","https://openalex.org/W2963420272","https://openalex.org/W2964309429","https://openalex.org/W2981682056","https://openalex.org/W3043547428","https://openalex.org/W3096831136","https://openalex.org/W3144890709","https://openalex.org/W3199003182","https://openalex.org/W4240726888","https://openalex.org/W4312497550","https://openalex.org/W4312933868","https://openalex.org/W4390873054","https://openalex.org/W4402774219","https://openalex.org/W4402904170","https://openalex.org/W4405521151","https://openalex.org/W4409347657","https://openalex.org/W4413156840","https://openalex.org/W4415798832","https://openalex.org/W7133250524"],"related_works":[],"abstract_inverted_index":{"Object":[0],"removal":[1,59,66,104,130],"aims":[2],"to":[3,81,133],"eliminate":[4],"undesired":[5],"objects":[6],"from":[7],"images":[8],"while":[9],"plausibly":[10],"restoring":[11],"the":[12,63],"underlying":[13],"content":[14],"with":[15,113,136],"high":[16],"visual":[17,93],"fidelity.":[18],"Existing":[19],"diffusion-based":[20],"methods":[21],"often":[22],"achieve":[23],"strong":[24],"results":[25],"by":[26],"relying":[27],"on":[28],"large-scale":[29],"model":[30],"finetuning,":[31],"auxiliary":[32],"control":[33],"networks,":[34],"or":[35],"powerful":[36],"diffusion":[37,70,79],"backbones,":[38],"which":[39],"incur":[40],"substantial":[41],"computational":[42],"overhead":[43],"and":[44,56,108,142],"limit":[45],"practical":[46,148],"efficiency.":[47],"In":[48],"this":[49],"work,":[50],"we":[51,95],"propose":[52],"SlimNet,":[53],"a":[54,77,97,114,147],"high-quality":[55],"efficient":[57],"object":[58,65,103],"framework":[60],"that":[61,101,126],"elicits":[62],"latent":[64],"capabilities":[67],"of":[68],"pretrained":[69],"models.":[71],"SlimNet":[72,127],"injects":[73],"lightweight":[74],"adapters":[75],"into":[76],"frozen":[78],"backbone":[80],"selectively":[82],"modulate":[83],"intermediate":[84],"representations,":[85],"avoiding":[86],"heavy":[87],"architectural":[88],"modifications.":[89],"To":[90],"further":[91],"improve":[92],"fidelity,":[94],"design":[96],"composite":[98],"perceptual":[99],"loss":[100],"enforces":[102],"accuracy,":[105],"background":[106],"preservation,":[107],"smooth":[109],"boundary":[110],"transitions,":[111],"together":[112],"semantic-aware":[115],"data":[116],"processing":[117],"pipeline":[118],"for":[119,150],"automatic":[120],"mask":[121],"generation.":[122],"Extensive":[123],"experiments":[124],"demonstrate":[125],"achieves":[128],"competitive":[129],"quality":[131],"compared":[132],"state-of-the-art":[134],"methods,":[135],"favorable":[137],"reductions":[138],"in":[139],"inference":[140],"time":[141],"VRAM":[143],"consumption,":[144],"making":[145],"it":[146],"solution":[149],"resource-constrained":[151],"multimedia":[152],"applications.":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-16T00:00:00"}