{"id":"https://openalex.org/W7134285109","doi":"https://doi.org/10.48550/arxiv.2603.06090","title":"DeepSight: Bridging Depth Maps and Language with a Depth-Driven Multimodal Model","display_name":"DeepSight: Bridging Depth Maps and Language with a Depth-Driven Multimodal Model","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7134285109","doi":"https://doi.org/10.48550/arxiv.2603.06090"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.06090","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128459185","display_name":"Hao Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128383589","display_name":"Hongbo Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hongbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128519499","display_name":"Yanyan Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yanyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128624963","display_name":"Bing Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Bing","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30093257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9907000064849854,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9907000064849854,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0027000000700354576,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.001500000013038516,"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/depth-map","display_name":"Depth map","score":0.6651999950408936},{"id":"https://openalex.org/keywords/depth-perception","display_name":"Depth perception","score":0.6018000245094299},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.532800018787384},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.45559999346733093},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4449000060558319},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4426000118255615},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.42250001430511475},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.421099990606308},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4065000116825104},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4009000062942505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757099986076355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7019000053405762},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.6651999950408936},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.6018000245094299},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5863000154495239},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4426000118255615},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.421099990606308},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C78201319","wikidata":"https://www.wikidata.org/wiki/Q685727","display_name":"Grayscale","level":3,"score":0.39980000257492065},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C113346285","wikidata":"https://www.wikidata.org/wiki/Q6804193","display_name":"Measured depth","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C84824328","wikidata":"https://www.wikidata.org/wiki/Q4633097","display_name":"2D to 3D conversion","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C183072630","wikidata":"https://www.wikidata.org/wiki/Q215932","display_name":"Depth of field","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.06090","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.06090","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.06090","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":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.06090","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.6094772815704346,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3],"(MLLMs)":[4],"have":[5],"achieved":[6],"impressive":[7],"performance":[8,165],"across":[9],"various":[10],"tasks":[11],"such":[12],"as":[13],"image":[14,56,181],"captioning":[15],"and":[16,94,109,125,201],"visual":[17,31,119],"question":[18,174],"answer(VQA);":[19],"however,":[20],"they":[21],"often":[22],"struggle":[23],"to":[24,45,82,129,147],"accurately":[25],"interpret":[26],"depth":[27,42,69,80,92,105,111,132,159,173,180,189,199],"information":[28],"inherent":[29],"in":[30,145,187,210],"data.":[32],"In":[33],"this":[34],"work,":[35],"we":[36,101,140,169],"introduce":[37],"DeepSight,":[38],"the":[39,65,75,95,122,142,154,164],"first":[40],"dedicated":[41],"MLLM":[43],"designed":[44],"enhance":[46],"three-dimensional":[47,212],"scene":[48],"understanding.":[49,213],"Unlike":[50],"conventional":[51],"methods":[52],"that":[53,195],"align":[54],"RGB":[55],"encodings":[57],"with":[58,90],"text,":[59],"our":[60,167],"approach":[61,135],"takes":[62],"advantage":[63],"of":[64,68,97,158,166],"unique":[66],"characteristics":[67],"images:":[70],"single-channel":[71],"grayscale":[72],"images":[73,120],"where":[74],"pixel":[76],"values":[77],"directly":[78],"reflect":[79],"cues":[81],"improve":[83],"spatial":[84],"reasoning.":[85],"To":[86,162],"address":[87],"challenges":[88],"associated":[89],"limited":[91],"data":[93],"inadequacy":[96],"simple":[98],"channel":[99],"replication,":[100],"construct":[102],"a":[103,110,171,206],"novel":[104],"image-text":[106],"pair":[107],"dataset":[108],"instruction":[112],"dataset.":[113],"Depth":[114],"maps":[115],"are":[116],"generated":[117],"from":[118],"using":[121],"GLPN":[123],"model,":[124,168],"GPT-4":[126],"is":[127],"employed":[128],"curate":[130],"corresponding":[131],"instructions,":[133],"an":[134],"validated":[136],"by":[137],"LLaVA.":[138],"Additionally,":[139],"modify":[141],"ViT":[143],"encoder":[144],"CLIP":[146],"incorporate":[148],"local":[149],"object":[150],"information,":[151],"thereby":[152],"capturing":[153],"subtle":[155],"continuous":[156],"variations":[157],"more":[160],"effectively.":[161],"evaluate":[163],"develop":[170],"comprehensive":[172],"answer":[175],"benchmark":[176],"based":[177],"on":[178],"existing":[179],"datasets,":[182],"which":[183],"rigorously":[184],"assesses":[185],"understanding":[186],"typical":[188],"map":[190],"scenarios.":[191],"Experimental":[192],"results":[193],"demonstrate":[194],"DeepSight":[196],"significantly":[197],"enhances":[198],"perception":[200],"downstream":[202],"task":[203],"performance,":[204],"marking":[205],"substantial":[207],"step":[208],"forward":[209],"multimodal":[211]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-03-10T00:00:00"}