{"id":"https://openalex.org/W4416748067","doi":"https://doi.org/10.1109/iros60139.2025.11246278","title":"DiFuse-Net: RGB and Dual-Pixel Depth Estimation using Window Bi-directional Parallax Attention and Cross-modal Transfer Learning","display_name":"DiFuse-Net: RGB and Dual-Pixel Depth Estimation using Window Bi-directional Parallax Attention and Cross-modal Transfer Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748067","doi":"https://doi.org/10.1109/iros60139.2025.11246278"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5048229460","display_name":"Kunal Swami","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kunal Swami","raw_affiliation_strings":["Samsung Research India,Visual Intelligence Team,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research India,Visual Intelligence Team,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109285337","display_name":"Debtanu Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Debtanu Gupta","raw_affiliation_strings":["Samsung Research India,Visual Intelligence Team,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research India,Visual Intelligence Team,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049309688","display_name":"Amrit Kumar Muduli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amrit Kumar Muduli","raw_affiliation_strings":["Samsung Research India,Visual Intelligence Team,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research India,Visual Intelligence Team,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120048443","display_name":"Chirag Jaiswal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chirag Jaiswal","raw_affiliation_strings":["Samsung Research India,Visual Intelligence Team,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research India,Visual Intelligence Team,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110528408","display_name":"Pankaj Bajpai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pankaj Kumar Bajpai","raw_affiliation_strings":["Samsung Research India,Visual Intelligence Team,Bangalore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research India,Visual Intelligence Team,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.32471443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3557","last_page":"3564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9656999707221985,"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":0.9656999707221985,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.006800000090152025,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10741","display_name":"Video Coding and Compression Technologies","score":0.004000000189989805,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/rgb-color-model","display_name":"RGB color model","score":0.7031000256538391},{"id":"https://openalex.org/keywords/parallax","display_name":"Parallax","score":0.6668999791145325},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.585099995136261},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.44179999828338623},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4163999855518341},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4050000011920929},{"id":"https://openalex.org/keywords/stereo-cameras","display_name":"Stereo cameras","score":0.3921000063419342},{"id":"https://openalex.org/keywords/rectification","display_name":"Rectification","score":0.37610000371932983},{"id":"https://openalex.org/keywords/depth-map","display_name":"Depth map","score":0.37439998984336853}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7968000173568726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748199999332428},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7318000197410583},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.7031000256538391},{"id":"https://openalex.org/C15759828","wikidata":"https://www.wikidata.org/wiki/Q165074","display_name":"Parallax","level":2,"score":0.6668999791145325},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.585099995136261},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.44179999828338623},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C35861506","wikidata":"https://www.wikidata.org/wiki/Q17141434","display_name":"Stereo cameras","level":3,"score":0.3921000063419342},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.37610000371932983},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.37439998984336853},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C2987632653","wikidata":"https://www.wikidata.org/wiki/Q7611220","display_name":"Stereo image","level":3,"score":0.31299999356269836},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C68537008","wikidata":"https://www.wikidata.org/wiki/Q247932","display_name":"Stereopsis","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C23379248","wikidata":"https://www.wikidata.org/wiki/Q200904","display_name":"Epipolar geometry","level":3,"score":0.30320000648498535},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C5799516","wikidata":"https://www.wikidata.org/wiki/Q4110915","display_name":"Visual odometry","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C185078393","wikidata":"https://www.wikidata.org/wiki/Q313783","display_name":"Stereo camera","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1677182931","https://openalex.org/W1901129140","https://openalex.org/W2104974755","https://openalex.org/W2108598243","https://openalex.org/W2115579991","https://openalex.org/W2259424905","https://openalex.org/W2798373498","https://openalex.org/W2808434111","https://openalex.org/W2963163009","https://openalex.org/W2963760790","https://openalex.org/W2981612893","https://openalex.org/W3007962889","https://openalex.org/W3032997361","https://openalex.org/W3034316458","https://openalex.org/W3035563424","https://openalex.org/W3087980862","https://openalex.org/W3097660860","https://openalex.org/W3109494165","https://openalex.org/W3110381689","https://openalex.org/W3177732058","https://openalex.org/W4226265017","https://openalex.org/W4312871721","https://openalex.org/W4386066351","https://openalex.org/W4386076576"],"related_works":[],"abstract_inverted_index":{"Depth":[0],"estimation":[1,180],"is":[2],"crucial":[3],"for":[4,50],"intelligent":[5],"systems,":[6],"enabling":[7],"applications":[8],"from":[9,89],"autonomous":[10],"navigation":[11],"to":[12,69,77,98,111,119],"augmented":[13],"reality.":[14],"While":[15],"traditional":[16],"stereo":[17,167,171,178],"and":[18,27,53,93,131,143,173,176],"active":[19],"depth":[20,56,100],"sensors":[21],"have":[22],"limitations":[23,123],"in":[24,33,116],"cost,":[25],"power,":[26],"robustness,":[28],"dual-pixel":[29],"(DP)":[30],"technology,":[31],"ubiquitous":[32],"modern":[34],"cameras,":[35],"offers":[36],"a":[37,44,60,105,150],"compelling":[38],"alternative.":[39],"This":[40],"paper":[41],"introduces":[42],"DiFuse-Net,":[43],"novel":[45,165],"modality":[46],"decoupled":[47],"network":[48],"design":[49],"disentangled":[51],"RGB":[52,91],"DP":[54,73,142],"based":[55],"estimation.":[57],"DiFuse-Net":[58],"features":[59,95],"window":[61],"bi-directional":[62],"parallax":[63],"attention":[64],"mechanism":[65,110],"(WBiPAM)":[66],"specifically":[67],"designed":[68],"capture":[70],"the":[71,90,117,122,134,141],"subtle":[72],"disparity":[74,179],"cues":[75],"unique":[76],"smartphone":[78],"cameras":[79],"with":[80,121],"small":[81],"aperture.":[82],"A":[83],"separate":[84],"encoder":[85],"extracts":[86],"contextual":[87],"information":[88],"image,":[92],"these":[94],"are":[96],"fused":[97],"enhance":[99],"prediction.":[101],"We":[102],"also":[103],"propose":[104],"Cross-modal":[106],"Transfer":[107],"Learning":[108],"(CmTL)":[109],"utilize":[112],"large-scale":[113,126],"RGB-D":[114],"datasets":[115],"literature":[118],"cope":[120],"of":[124,133],"obtaining":[125],"RGB-DP-D":[127,154],"dataset.":[128],"Our":[129],"evaluation":[130],"comparison":[132],"proposed":[135],"method":[136],"demonstrates":[137],"its":[138],"superiority":[139],"over":[140],"stereo-based":[144],"baseline":[145],"methods.":[146],"Additionally,":[147],"we":[148],"contribute":[149],"new,":[151],"high-quality,":[152],"real-world":[153],"training":[155],"dataset,":[156,161],"named":[157],"Dual-Camera":[158],"Dual-Pixel":[159],"(DCDP)":[160],"created":[162],"using":[163],"our":[164],"symmetric":[166],"camera":[168],"hardware":[169],"setup,":[170],"calibration":[172],"rectification":[174],"protocol,":[175],"AI":[177],"method.":[181]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}