{"id":"https://openalex.org/W7128486844","doi":"https://doi.org/10.1109/access.2026.3663209","title":"Denoising With a Compass: Geometry-Guided Diffusion for Robust Low-Quality Image Segmentation","display_name":"Denoising With a Compass: Geometry-Guided Diffusion for Robust Low-Quality Image Segmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7128486844","doi":"https://doi.org/10.1109/access.2026.3663209"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3663209","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3663209","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3663209","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124748377","display_name":"Maoyang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Maoyang Xu","raw_affiliation_strings":["Century College, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-6735-3739","affiliations":[{"raw_affiliation_string":"Century College, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102490614","display_name":"Nana He","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nana He","raw_affiliation_strings":["Century College, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-8291-5278","affiliations":[{"raw_affiliation_string":"Century College, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125566353","display_name":"Jing Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Century College, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Century College, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077865965","display_name":"Fujiao Ju","orcid":"https://orcid.org/0000-0002-0188-6996"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fujiao Ju","raw_affiliation_strings":["Beijing University of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":7.2709,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9453749,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"14","issue":null,"first_page":"39512","last_page":"39533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.3822999894618988,"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/T11019","display_name":"Image Enhancement Techniques","score":0.3822999894618988,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.24719999730587006,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.15080000460147858,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.5921000242233276},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5853999853134155},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5461999773979187},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.49790000915527344},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.49630001187324524},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44940000772476196},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43689998984336853},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.4325000047683716},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4296000003814697},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.40700000524520874}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7843000292778015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7050999999046326},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6866000294685364},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5921000242233276},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5853999853134155},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5461999773979187},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4296000003814697},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.40700000524520874},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4000000059604645},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.38580000400543213},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.36570000648498535},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.34279999136924744},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C193536780","wikidata":"https://www.wikidata.org/wiki/Q1513153","display_name":"Edge detection","level":4,"score":0.3019999861717224},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C32209215","wikidata":"https://www.wikidata.org/wiki/Q5535483","display_name":"Geometric flow","level":3,"score":0.2773999869823456},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.26669999957084656},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.2648000121116638},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3663209","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3663209","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:413d9c7637554e7091e6991366098219","is_oa":true,"landing_page_url":"https://doaj.org/article/413d9c7637554e7091e6991366098219","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 39512-39533 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3663209","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3663209","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3964532910","display_name":null,"funder_award_id":"4242016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5153687263","display_name":null,"funder_award_id":"62572018","funder_id":"https://openalex.org/F4320334977","funder_display_name":"Beijing Municipal Natural Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334977","display_name":"Beijing Municipal Natural Science Foundation","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2108598243","https://openalex.org/W2340897893","https://openalex.org/W2508457857","https://openalex.org/W2560622558","https://openalex.org/W2594519801","https://openalex.org/W2607333215","https://openalex.org/W2962793481","https://openalex.org/W2963150697","https://openalex.org/W2963814095","https://openalex.org/W2964309882","https://openalex.org/W2968638474","https://openalex.org/W2986422266","https://openalex.org/W3120800187","https://openalex.org/W3138516171","https://openalex.org/W3212516020","https://openalex.org/W4312933868","https://openalex.org/W4385245566","https://openalex.org/W4390873101","https://openalex.org/W4390874575","https://openalex.org/W4391053327","https://openalex.org/W4401075918","https://openalex.org/W4401247300","https://openalex.org/W4402703114","https://openalex.org/W4406769472","https://openalex.org/W4407900684","https://openalex.org/W4408343759","https://openalex.org/W4411224879","https://openalex.org/W4411593463","https://openalex.org/W4414316117"],"related_works":[],"abstract_inverted_index":{"In":[0],"the":[1,10,68,72,93,104,125,129,151,156,179],"field":[2],"of":[3,128,181],"image":[4,51,210],"segmentation,":[5],"foundation":[6],"models":[7,183],"such":[8,38,164],"as":[9,39,100,119,165,172],"Segment":[11],"Anything":[12],"Model":[13],"(SAM)":[14],"demonstrate":[15,169],"remarkable":[16],"zero-shot":[17],"generalization":[18],"capabilities":[19],"on":[20,161,186],"high-quality":[21],"images.":[22],"However,":[23],"their":[24],"performance":[25,180],"significantly":[26,177],"deteriorates":[27],"when":[28],"applied":[29],"to":[30,123,154],"low-quality":[31,187],"images":[32,153,188],"commonly":[33],"encountered":[34],"in":[35],"real-world":[36],"scenarios,":[37],"those":[40],"corrupted":[41],"by":[42],"noise,":[43],"blur,":[44],"or":[45,115],"low-light":[46],"conditions.":[47],"Although":[48],"existing":[49],"diffusion-based":[50],"enhancement":[52,105],"methods":[53],"can":[54],"improve":[55],"visual":[56,195],"quality,":[57],"they":[58],"often":[59],"introduce":[60],"\"hallucinated\"":[61],"details":[62],"that":[63,144,170],"are":[64],"geometrically":[65],"inconsistent":[66],"with":[67],"input,":[69],"thereby":[70],"compromising":[71],"structural":[73,121],"accuracy":[74],"essential":[75],"for":[76,92,207],"segmentation":[77,182],"tasks.":[78],"To":[79],"address":[80],"this":[81,83],"issue,":[82],"paper":[84],"proposes":[85],"a":[86,101,120,133,140,146,173,204],"geometry-guided":[87],"diffusion":[88,130],"model":[89,131],"(G\u00b2D),":[90],"which,":[91],"first":[94],"time,":[95],"explicitly":[96],"incorporates":[97],"geometric":[98,110,141,199],"consistency":[99,142],"constraint":[102],"into":[103],"process.":[106],"G\u00b2D":[107],"leverages":[108],"pre-trained":[109],"prior":[111],"extractors":[112],"(e.g.,":[113],"depth":[114],"edge":[116],"estimation":[117],"models)":[118],"\"compass\"":[122],"guide":[124],"denoising":[126],"process":[127],"via":[132],"cross-attention":[134],"mechanism.":[135],"Moreover,":[136],"we":[137],"innovatively":[138],"propose":[139],"loss":[143],"forms":[145],"self-supervised":[147],"closed":[148],"loop,":[149],"enforcing":[150],"enhanced":[152],"preserve":[155],"original":[157],"scene":[158],"layout.":[159],"Experiments":[160],"challenging":[162],"benchmarks":[163],"ImageNet-C":[166],"and":[167],"ACDC":[168],"G\u00b2D,":[171],"plug-and-play":[174],"pre-processing":[175],"module,":[176],"improves":[178],"like":[184],"SAM":[185],"without":[189],"requiring":[190],"fine-tuning.":[191],"By":[192],"effectively":[193],"restoring":[194],"appearance":[196],"while":[197],"preserving":[198],"structure,":[200],"our":[201],"work":[202],"provides":[203],"new":[205],"direction":[206],"task-oriented":[208],"robust":[209],"enhancement.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-02-11T00:00:00"}