{"id":"https://openalex.org/W4404990162","doi":"https://doi.org/10.1109/tmi.2026.3671423","title":"Self-Supervised Monocular Depth and Pose Estimation for Endoscopy With Latent Priors","display_name":"Self-Supervised Monocular Depth and Pose Estimation for Endoscopy With Latent Priors","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W4404990162","doi":"https://doi.org/10.1109/tmi.2026.3671423","pmid":"https://pubmed.ncbi.nlm.nih.gov/41801778"},"language":"en","primary_location":{"id":"doi:10.1109/tmi.2026.3671423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmi.2026.3671423","pdf_url":null,"source":{"id":"https://openalex.org/S58069681","display_name":"IEEE Transactions on Medical Imaging","issn_l":"0278-0062","issn":["0278-0062","1558-254X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Medical Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.17790","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102732730","display_name":"Ziang Xu","orcid":"https://orcid.org/0000-0002-3883-3716"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ziang Xu","raw_affiliation_strings":["Department of Engineering, University of Oxford, Oxford, U.K"],"raw_orcid":"https://orcid.org/0000-0002-3883-3716","affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100663126","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-1381-8798"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["Department of Engineering, University of Oxford, Oxford, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596877","display_name":"Yang Hu","orcid":"https://orcid.org/0000-0002-1759-5085"},"institutions":[{"id":"https://openalex.org/I153648349","display_name":"University of Leicester","ror":"https://ror.org/04h699437","country_code":"GB","type":"education","lineage":["https://openalex.org/I153648349"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang Hu","raw_affiliation_strings":["University of Leicester, Leicester, U.K"],"raw_orcid":"https://orcid.org/0000-0002-4856-5014","affiliations":[{"raw_affiliation_string":"University of Leicester, Leicester, U.K","institution_ids":["https://openalex.org/I153648349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377496","display_name":"Chenyu Zhang","orcid":"https://orcid.org/0009-0000-3604-0643"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chenyu Zhang","raw_affiliation_strings":["Department of Engineering, University of Oxford, Oxford, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090352318","display_name":"James E. East","orcid":"https://orcid.org/0000-0001-8035-3700"},"institutions":[{"id":"https://openalex.org/I2801809904","display_name":"Nuffield Orthopaedic Centre","ror":"https://ror.org/0036ate90","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2801809904","https://openalex.org/I4210147381"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James East","raw_affiliation_strings":["Nuffield Department of Clinical Medicine, Experimental Medicine Division, University of Oxford, Oxford, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuffield Department of Clinical Medicine, Experimental Medicine Division, University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I2801809904","https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080765299","display_name":"Sharib Ali","orcid":"https://orcid.org/0000-0003-1313-3542"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sharib Ali","raw_affiliation_strings":["School of Computer Science, University of Leeds, Leeds, U.K"],"raw_orcid":"https://orcid.org/0000-0003-1313-3542","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Leeds, Leeds, U.K","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027416348","display_name":"Jens Rittscher","orcid":"https://orcid.org/0000-0002-8528-8298"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jens Rittscher","raw_affiliation_strings":["Department of Engineering, University of Oxford, Oxford, U.K"],"raw_orcid":"https://orcid.org/0000-0002-8528-8298","affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Oxford, Oxford, U.K","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00080201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"45","issue":"6","first_page":"3203","last_page":"3215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.7843777537345886},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6606694459915161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.630805253982544},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5673360228538513},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5360721945762634},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44988563656806946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4145791828632355},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4116722643375397},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33325865864753723},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32333922386169434},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3214271664619446},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.22406655550003052},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05885836482048035}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7843777537345886},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6606694459915161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.630805253982544},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5673360228538513},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5360721945762634},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44988563656806946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4145791828632355},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4116722643375397},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33325865864753723},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32333922386169434},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3214271664619446},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.22406655550003052},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05885836482048035},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000098446","descriptor_name":"Autoencoder","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098446","descriptor_name":"Autoencoder","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016099","descriptor_name":"Endoscopy, Gastrointestinal","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016099","descriptor_name":"Endoscopy, Gastrointestinal","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D021621","descriptor_name":"Imaging, Three-Dimensional","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1109/tmi.2026.3671423","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmi.2026.3671423","pdf_url":null,"source":{"id":"https://openalex.org/S58069681","display_name":"IEEE Transactions on Medical Imaging","issn_l":"0278-0062","issn":["0278-0062","1558-254X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Medical Imaging","raw_type":"journal-article"},{"id":"pmid:41801778","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41801778","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on medical imaging","raw_type":null},{"id":"pmh:oai:arXiv.org:2411.17790","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.17790","pdf_url":"https://arxiv.org/pdf/2411.17790","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:arXiv.org:2411.17790","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2411.17790","pdf_url":"https://arxiv.org/pdf/2411.17790","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.17790","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.17790","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:oai:arXiv.org:2411.17790","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.17790","pdf_url":"https://arxiv.org/pdf/2411.17790","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1954408126","display_name":"Real-time High-Fidelity Augmented Reality in Laparoscopic Liver Resection","funder_award_id":"UKRI914","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G503076605","display_name":null,"funder_award_id":"SBF00101191","funder_id":"https://openalex.org/F4320320241","funder_display_name":"Academy of Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320311496","display_name":"Ludwig Institute for Cancer Research","ror":"https://ror.org/05qdwtz81"},{"id":"https://openalex.org/F4320320241","display_name":"Academy of Medical Sciences","ror":"https://ror.org/00c489v88"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320336045","display_name":"NIHR Oxford Biomedical Research Centre","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404990162.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3168675052","https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559"],"abstract_inverted_index":{"Accurate":[0],"3D":[1],"reconstruction":[2],"in":[3,44,221],"endoscopy":[4,27],"enables":[5,189],"quantitative":[6],"and":[7,21,31,55,64,86,117,126,192,202,209,224,230],"holistic":[8],"lesion":[9],"characterization":[10],"within":[11,101],"the":[12,81,159,176,197],"gastrointestinal":[13],"(GI)":[14],"tract.":[15],"To":[16,121],"achieve":[17],"this,":[18],"reliable":[19],"depth":[20,54,74,82,89,191,223],"pose":[22,56,96,106,124,144,163,193,225],"estimation":[23,57],"is":[24],"required.":[25],"However,":[26],"systems":[28],"are":[29,232],"monocular,":[30],"existing":[32],"methods":[33,220],"relying":[34],"on":[35,151,206],"synthetic":[36],"datasets":[37,211],"or":[38],"complex":[39,200],"models":[40],"often":[41],"lack":[42],"generalizability":[43],"challenging":[45,183],"endoscopic":[46,177,222],"conditions.":[47,184],"We":[48],"propose":[49],"a":[50,61,65,102,130,147,165],"robust":[51],"self-supervised":[52,219],"monocular":[53],"framework":[58],"that":[59,134],"incorporates":[60],"StyleGAN-based":[62],"generator":[63,71],"Variational":[66],"Autoencoder":[67],"(VAE).":[68],"The":[69],"StyleGAN":[70],"leverages":[72],"extensive":[73],"scenes":[75],"from":[76,138,146],"natural":[77,139,153],"images":[78],"to":[79,111,157],"condition":[80],"network,":[83],"enhancing":[84],"realism":[85],"robustness":[87],"of":[88,162],"predictions":[90],"through":[91,164],"latent":[92,109,160],"feature":[93],"priors.":[94],"For":[95],"estimation,":[97],"we":[98,128],"reformulate":[99],"it":[100],"VAE":[103],"framework,":[104],"treating":[105],"transitions":[107],"as":[108],"variables":[110],"regularize":[112],"scale,":[113],"stabilize":[114],"z-axis":[115],"prominence,":[116],"improve":[118],"x-y":[119],"sensitivity.":[120],"further":[122],"enhance":[123],"stability":[125],"generalizability,":[127],"introduce":[129],"prior":[131],"transfer":[132],"module":[133],"distills":[135],"motion":[136,173],"knowledge":[137],"scene":[140,154],"SLAM":[141,149],"systems.":[142],"Specifically,":[143],"priors":[145,174],"pretrained":[148],"model-supervised":[150],"large-scale":[152],"datasets-are":[155],"used":[156],"guide":[158],"distribution":[161],"KL-divergence":[166],"reparameterization.":[167],"This":[168,185],"mechanism":[169],"effectively":[170,195],"transfers":[171],"structural":[172],"into":[175],"domain,":[178],"improving":[179],"trajectory":[180],"consistency":[181],"under":[182],"dual":[186],"refinement":[187],"pipeline":[188],"accurate":[190],"predictions,":[194],"addressing":[196],"GI":[198],"tract's":[199],"textures":[201],"lighting.":[203],"Extensive":[204],"evaluations":[205],"SimCol,":[207],"C3VD,":[208],"EndoSLAM":[210],"confirm":[212],"our":[213],"framework's":[214],"superior":[215],"performance":[216],"over":[217],"published":[218],"estimation.":[226],"All":[227],"data":[228],"descriptions":[229],"code":[231],"available":[233],"at":[234],"https://github.com/EricXuziang/Self-supervised-with-Latent-Priors.git.":[235]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2024-12-05T00:00:00"}