{"id":"https://openalex.org/W4411631843","doi":"https://doi.org/10.1145/3731715.3733319","title":"Efficient Monocular Depth Estimation Via Single-Step Latent Diffusion Models","display_name":"Efficient Monocular Depth Estimation Via Single-Step Latent Diffusion Models","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411631843","doi":"https://doi.org/10.1145/3731715.3733319"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733319","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077028026","display_name":"Zhiyong Huo","orcid":"https://orcid.org/0000-0002-7192-2593"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiyong Huo","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062916182","display_name":"Zhendong Wang","orcid":"https://orcid.org/0009-0008-2400-9137"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhendong Wang","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5077028026"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16230029,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"542","last_page":"549"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9998999834060669,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9998999834060669,"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/T10638","display_name":"Optical measurement and interference techniques","score":0.9979000091552734,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9939000010490417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.7021029591560364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6291967034339905},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5999121069908142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5531206130981445},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4951254427433014},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46276015043258667},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06288868188858032}],"concepts":[{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.7021029591560364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6291967034339905},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5999121069908142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5531206130981445},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4951254427433014},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46276015043258667},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06288868188858032},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733319","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733319","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2115579991","https://openalex.org/W2594519801","https://openalex.org/W2741885505","https://openalex.org/W3004819717","https://openalex.org/W3081167590","https://openalex.org/W3097660860","https://openalex.org/W3119361882","https://openalex.org/W3174458495","https://openalex.org/W3203887644","https://openalex.org/W4214520160","https://openalex.org/W4309505380","https://openalex.org/W4312819733","https://openalex.org/W4312933868","https://openalex.org/W4320167896","https://openalex.org/W4386723894","https://openalex.org/W4389667560","https://openalex.org/W4390871919","https://openalex.org/W4390873429","https://openalex.org/W4402753888","https://openalex.org/W4402961751"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Monocular":[0],"depth":[1,14,34,64],"estimation":[2],"is":[3,86,118],"a":[4,17,20,59,71,121],"fundamental":[5],"task":[6],"in":[7,139],"computer":[8],"vision,":[9],"aiming":[10],"to":[11,45,92],"recover":[12],"the":[13,49,77,113,133],"information":[15,35],"of":[16,51,83,115],"scene":[18],"from":[19,28,66],"RGB":[21,67],"image.":[22],"Traditional":[23],"latent":[24],"diffusion":[25],"models":[26],"start":[27],"Gaussian":[29],"noise":[30],"and":[31,48,98,104,142],"progressively":[32],"restore":[33],"through":[36,120],"iterative":[37],"denoising,":[38],"during":[39],"which":[40],"errors":[41,106],"may":[42],"accumulate,":[43],"leading":[44],"blurred":[46],"boundaries":[47],"loss":[50],"fine":[52],"details.":[53],"In":[54,111],"this":[55],"work,":[56],"we":[57],"propose":[58],"method":[60,101],"that":[61,132],"directly":[62],"predicts":[63],"maps":[65],"images":[68],"by":[69],"leveraging":[70],"pre-trained":[72],"Stable":[73,84],"Diffusion":[74,85],"model":[75],"as":[76,88],"generative":[78],"backbone.":[79],"The":[80,100],"denoising":[81],"U-Net":[82],"redefined":[87],"an":[89],"encoder-decoder":[90],"architecture":[91],"enable":[93],"more":[94],"efficient":[95],"feature":[96],"extraction":[97],"reconstruction.":[99],"reduces":[102],"artifacts":[103],"cumulative":[105],"while":[107],"improving":[108],"inference":[109],"speed.":[110],"addition,":[112],"control":[114],"depth-specific":[116],"features":[117],"enhanced":[119],"CLIP-based":[122],"conditional":[123],"generation":[124],"mechanism.":[125],"Extensive":[126],"evaluations":[127],"on":[128],"benchmark":[129],"datasets":[130],"demonstrate":[131],"proposed":[134],"approach":[135],"achieves":[136],"competitive":[137],"performance":[138],"both":[140],"accuracy":[141],"efficiency.":[143]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}