{"id":"https://openalex.org/W7140225076","doi":"https://doi.org/10.1109/tcsvt.2026.3677060","title":"DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation","display_name":"DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7140225076","doi":"https://doi.org/10.1109/tcsvt.2026.3677060"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2026.3677060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3677060","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-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":null,"display_name":"Yan Gong","orcid":"https://orcid.org/0000-0002-3148-8286"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4391767639","display_name":"State Key Laboratory of Robotics and Systems","ror":"https://ror.org/015m77g16","country_code":"CN","type":"facility","lineage":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Gong","raw_affiliation_strings":["State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-3148-8286","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianli Lu","orcid":"https://orcid.org/0000-0002-8459-9211"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4391767639","display_name":"State Key Laboratory of Robotics and Systems","ror":"https://ror.org/015m77g16","country_code":"CN","type":"facility","lineage":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianli Lu","raw_affiliation_strings":["State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-8459-9211","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yongsheng Gao","orcid":"https://orcid.org/0000-0002-1555-8328"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4391767639","display_name":"State Key Laboratory of Robotics and Systems","ror":"https://ror.org/015m77g16","country_code":"CN","type":"facility","lineage":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongsheng Gao","raw_affiliation_strings":["State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-1555-8328","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jie Zhao","orcid":"https://orcid.org/0000-0002-6086-9387"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4391767639","display_name":"State Key Laboratory of Robotics and Systems","ror":"https://ror.org/015m77g16","country_code":"CN","type":"facility","lineage":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhao","raw_affiliation_strings":["State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-6086-9387","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4391767639"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaojuan Zhang","orcid":"https://orcid.org/0000-0002-7719-8890"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaojuan Zhang","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Fusionopolis, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7719-8890","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Fusionopolis, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":null,"display_name":"Susanto Rahardja","orcid":"https://orcid.org/0000-0003-0831-6934"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Susanto Rahardja","raw_affiliation_strings":["College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0831-6934","affiliations":[{"raw_affiliation_string":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.35507653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"7","first_page":"9309","last_page":"9321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.760699987411499,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.760699987411499,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.08089999854564667,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0333000011742115,"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/discriminative-model","display_name":"Discriminative model","score":0.7890999913215637},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6323000192642212},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49889999628067017},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.46630001068115234},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4496000111103058},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4278999865055084},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41589999198913574},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.40860000252723694},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.37959998846054077}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7890999913215637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735999822616577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6563000082969666},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5444999933242798},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49889999628067017},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4278999865055084},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.35120001435279846},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3301999866962433},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3179999887943268},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.31709998846054077},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2761000096797943},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.258899986743927},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2026.3677060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2026.3677060","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7638648748397827}],"awards":[{"id":"https://openalex.org/G3132466192","display_name":null,"funder_award_id":"LH2021E076","funder_id":"https://openalex.org/F4320323085","funder_display_name":"Natural Science Foundation of Heilongjiang Province"},{"id":"https://openalex.org/G5602747375","display_name":null,"funder_award_id":"52025054","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5860290815","display_name":null,"funder_award_id":"2025ZD1603200","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G7616631648","display_name":null,"funder_award_id":"52025054","funder_id":"https://openalex.org/F4320333688","funder_display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320333688","display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Indoor":[0],"semantic":[1],"segmentation":[2,71],"is":[3,163,176],"fundamental":[4],"to":[5,106,131],"computer":[6],"vision":[7],"and":[8,18,27,39,43,52,77,96,109,125,140,151,157],"robotics,":[9],"supporting":[10],"applications":[11],"such":[12],"as":[13],"autonomous":[14],"navigation,":[15],"augmented":[16],"reality,":[17],"smart":[19],"environments.":[20],"Although":[21],"RGB-D":[22,68,128,139],"fusion":[23,120],"leverages":[24],"complementary":[25],"appearance":[26],"geometric":[28],"cues,":[29,111],"existing":[30],"methods":[31],"often":[32],"depend":[33],"on":[34,136,166],"computationally":[35],"intensive":[36],"cross-attention":[37],"mechanisms":[38],"insufficiently":[40],"model":[41],"intra-":[42],"inter-modal":[44,79,98],"feature":[45,50],"relationships,":[46],"resulting":[47],"in":[48],"imprecise":[49],"alignment":[51],"limited":[53],"discriminative":[54],"representation.":[55],"To":[56],"address":[57],"these":[58],"challenges,":[59],"we":[60],"propose":[61],"DiffPixelFormer,":[62],"a":[63,118],"differential":[64],"pixel-aware":[65],"Transformer":[66],"for":[67],"indoor":[69],"scene":[70,132],"that":[72,144],"simultaneously":[73],"enhances":[74],"intra-modal":[75,91],"representations":[76],"models":[78,97],"interactions.":[80],"At":[81],"its":[82,161],"core,":[83],"the":[84,101,137,167],"Intra-Inter":[85],"Modal":[86],"Interaction":[87],"Block":[88],"(IIMIB)":[89],"captures":[90],"long-range":[92],"dependencies":[93],"via":[94],"self-attention":[95],"interactions":[99],"with":[100],"Differential\u2013Shared":[102],"Inter-Modal":[103],"(DSIM)":[104],"module":[105],"disentangle":[107],"modality-specific":[108],"shared":[110],"enabling":[112],"fine-grained,":[113],"pixel-level":[114],"cross-modal":[115],"alignment.":[116],"Furthermore,":[117],"dynamic":[119],"strategy":[121],"balances":[122],"modality":[123],"contributions":[124],"fully":[126],"exploits":[127],"information":[129],"according":[130],"characteristics.":[133],"Extensive":[134],"experiments":[135],"SUN":[138],"NYUDv2":[141],"benchmarks":[142],"demonstrate":[143],"DiffPixelFormer-L":[145],"achieves":[146],"mIoU":[147],"scores":[148],"of":[149],"54.28%":[150],"59.95%,":[152],"outperforming":[153],"DFormer-L":[154],"by":[155],"1.78%":[156],"2.75%,":[158],"respectively.":[159],"Moreover,":[160],"effectiveness":[162],"further":[164],"validated":[165],"large-scale":[168],"ScanNetv2":[169],"dataset,":[170],"indicating":[171],"strong":[172],"generalization":[173],"capability.":[174],"Code":[175],"available":[177],"at":[178],"https://github.com/gongyan1/DiffPixelFormer.":[179]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-25T00:00:00"}
