{"id":"https://openalex.org/W4416371263","doi":"https://doi.org/10.1109/bibm66473.2025.11357186","title":"HAVIR: Hierarchical Vision to Image Reconstruction Using Clip-Guided Versatile Diffusion","display_name":"HAVIR: Hierarchical Vision to Image Reconstruction Using Clip-Guided Versatile Diffusion","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W4416371263","doi":"https://doi.org/10.1109/bibm66473.2025.11357186"},"language":"en","primary_location":{"id":"doi:10.1109/bibm66473.2025.11357186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11357186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.03122","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100784917","display_name":"Shiyi Zhang","orcid":"https://orcid.org/0000-0002-8466-3359"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shiyi Zhang","raw_affiliation_strings":["College of Engineering, Southern University of Science and Technology,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Southern University of Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071577305","display_name":"Liang Dong","orcid":"https://orcid.org/0000-0002-8585-1087"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Liang","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024833275","display_name":"Hairong Zheng","orcid":"https://orcid.org/0000-0002-8558-5102"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hairong Zheng","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010510025","display_name":"Yihang Zhou","orcid":"https://orcid.org/0000-0001-6354-1259"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihang Zhou","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,Shenzhen,China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100784917"],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34703464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4414","last_page":"4419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.8342999815940857,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.8342999815940857,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.024299999698996544,"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/T10427","display_name":"Visual perception and processing mechanisms","score":0.02370000071823597,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.6815999746322632},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.503600001335144},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48500001430511475},{"id":"https://openalex.org/keywords/visual-cortex","display_name":"Visual cortex","score":0.4478999972343445},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4302000105381012},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4083999991416931},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.40369999408721924},{"id":"https://openalex.org/keywords/visual-processing","display_name":"Visual processing","score":0.34619998931884766},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.32910001277923584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178000211715698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6873000264167786},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.6815999746322632},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5508000254631042},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.503600001335144},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C2779345533","wikidata":"https://www.wikidata.org/wiki/Q75785","display_name":"Visual cortex","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4302000105381012},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C2778251979","wikidata":"https://www.wikidata.org/wiki/Q7936617","display_name":"Visual processing","level":3,"score":0.34619998931884766},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3269999921321869},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.29750001430511475},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C205427263","wikidata":"https://www.wikidata.org/wiki/Q1931480","display_name":"Neuroinformatics","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.25859999656677246}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/bibm66473.2025.11357186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11357186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.03122","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.03122","pdf_url":"https://arxiv.org/pdf/2510.03122","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":"pmh:doi:10.48550/arxiv.2510.03122","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2510.03122","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.03122","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.03122","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.03122","pdf_url":"https://arxiv.org/pdf/2510.03122","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":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2145889472","https://openalex.org/W2119885245","https://openalex.org/W2058670155","https://openalex.org/W3171908098","https://openalex.org/W4403479245","https://openalex.org/W2949869422","https://openalex.org/W3004371658","https://openalex.org/W3120395234","https://openalex.org/W4200613736","https://openalex.org/W4386076190","https://openalex.org/W4386881720","https://openalex.org/W4387969592","https://openalex.org/W4402716025","https://openalex.org/W4403842057","https://openalex.org/W4402667902","https://openalex.org/W4409364707","https://openalex.org/W1631093856","https://openalex.org/W1971579779","https://openalex.org/W2133410812","https://openalex.org/W2963341661","https://openalex.org/W2098580305","https://openalex.org/W845365781","https://openalex.org/W4394596534","https://openalex.org/W4282830146"],"related_works":[],"abstract_inverted_index":{"The":[0],"reconstruction":[1],"of":[2,35,58,137],"visual":[3,27,60,70],"information":[4,88],"from":[5,32,80,89],"brain":[6],"activity":[7],"fosters":[8],"interdisciplinary":[9],"integration":[10],"between":[11],"neuroscience":[12],"and":[13,76,93,134,143],"computer":[14],"vision.":[15],"However,":[16],"existing":[17,145],"methods":[18],"still":[19],"face":[20],"challenges":[21],"in":[22,140],"accurately":[23],"recovering":[24],"highly":[25],"complex":[26,141],"stimuli.":[28],"This":[29],"difficulty":[30],"stems":[31],"the":[33,54,59,64,69,83,101,116,122,132],"characteristics":[34],"natural":[36],"scenes:":[37],"low-level":[38],"features":[39,44,79],"exhibit":[40],"heterogeneity,":[41],"while":[42,100],"high-level":[43],"show":[45],"semantic":[46,105,135],"entanglement":[47],"due":[48],"to":[49,120],"contextual":[50],"overlaps.":[51],"Inspired":[52],"by":[53],"hierarchical":[55,74],"representation":[56],"theory":[57],"cortex,":[61],"we":[62],"propose":[63],"HAVIR":[65,129],"model,":[66],"which":[67],"separates":[68],"cortex":[71],"into":[72,96,108],"two":[73],"regions":[75],"extracts":[77,86],"distinct":[78],"each.":[81],"Specifically,":[82],"Structural":[84],"Generator":[85],"structural":[87,133],"spatial":[90],"processing":[91,106],"voxels":[92,107],"converts":[94,104],"it":[95],"latent":[97],"diffusion":[98],"priors,":[99],"Semantic":[102],"Extractor":[103],"CLIP":[109],"embeddings.":[110],"These":[111],"components":[112],"are":[113],"integrated":[114],"via":[115],"Versatile":[117],"Diffusion":[118],"model":[119],"synthesize":[121],"final":[123],"image.":[124],"Experimental":[125],"results":[126],"demonstrate":[127],"that":[128],"enhances":[130],"both":[131],"quality":[136],"reconstructions,":[138],"even":[139],"scenes,":[142],"outperforms":[144],"models.":[146]},"counts_by_year":[],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}