{"id":"https://openalex.org/W7225615801","doi":"https://doi.org/10.3390/make8110371","title":"Quality-Driven Reinforcement Learning for Adaptive Loss Weighting in Survey-Vehicle Removal of Mobile Mapping Panoramas","display_name":"Quality-Driven Reinforcement Learning for Adaptive Loss Weighting in Survey-Vehicle Removal of Mobile Mapping Panoramas","publication_year":2026,"publication_date":"2026-11-08","ids":{"openalex":"https://openalex.org/W7225615801","doi":"https://doi.org/10.3390/make8110371"},"language":"en","primary_location":{"id":"doi:10.3390/make8110371","doi":"https://doi.org/10.3390/make8110371","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make8110371","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/make8110371","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066108041","display_name":"Luepol Pipanmekaporn","orcid":"https://orcid.org/0009-0005-5882-9342","observed_orcids":["https://orcid.org/0009-0005-5882-9342"]},"institutions":[{"id":"https://openalex.org/I82828225","display_name":"King Mongkut's University of Technology North Bangkok","ror":"https://ror.org/04fy6jb97","country_code":"TH","type":"education","lineage":["https://openalex.org/I82828225"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Luepol Pipanmekaporn","raw_affiliation_strings":["Department of Computer and Information Science, King Mongkut\u2019s University of Technology North Bangkok, Bangkok 10800, Thailand"],"raw_orcid":"https://orcid.org/0009-0005-5882-9342","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, King Mongkut\u2019s University of Technology North Bangkok, Bangkok 10800, Thailand","institution_ids":["https://openalex.org/I82828225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070023527","display_name":"Kanabadee Srisomboon","orcid":"https://orcid.org/0000-0002-3120-3324","observed_orcids":["https://orcid.org/0000-0002-3120-3324"]},"institutions":[{"id":"https://openalex.org/I82828225","display_name":"King Mongkut's University of Technology North Bangkok","ror":"https://ror.org/04fy6jb97","country_code":"TH","type":"education","lineage":["https://openalex.org/I82828225"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Kanabadee Srisomboon","raw_affiliation_strings":["Department of Electrical and Computer Engineering, King Mongkut\u2019s University of Technology North Bangkok, Bangkok 10800, Thailand"],"raw_orcid":"https://orcid.org/0000-0002-3120-3324","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, King Mongkut\u2019s University of Technology North Bangkok, Bangkok 10800, Thailand","institution_ids":["https://openalex.org/I82828225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049032225","display_name":"Wilaiporn Lee","orcid":"https://orcid.org/0000-0001-7484-0246","observed_orcids":["https://orcid.org/0000-0001-7484-0246"]},"institutions":[{"id":"https://openalex.org/I82828225","display_name":"King Mongkut's University of Technology North Bangkok","ror":"https://ror.org/04fy6jb97","country_code":"TH","type":"education","lineage":["https://openalex.org/I82828225"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Wilaiporn Lee","raw_affiliation_strings":["Department of Electrical and Computer Engineering, King Mongkut\u2019s University of Technology North Bangkok, Bangkok 10800, Thailand"],"raw_orcid":"https://orcid.org/0000-0001-7484-0246","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, King Mongkut\u2019s University of Technology North Bangkok, Bangkok 10800, Thailand","institution_ids":["https://openalex.org/I82828225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062169021","display_name":"Akara Prayote","orcid":"https://orcid.org/0009-0005-3887-5018","observed_orcids":["https://orcid.org/0009-0005-3887-5018"]},"institutions":[{"id":"https://openalex.org/I82828225","display_name":"King Mongkut's University of Technology North Bangkok","ror":"https://ror.org/04fy6jb97","country_code":"TH","type":"education","lineage":["https://openalex.org/I82828225"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Akara Prayote","raw_affiliation_strings":["Department of Computer and Information Science, King Mongkut\u2019s University of Technology North Bangkok, Bangkok 10800, Thailand"],"raw_orcid":"https://orcid.org/0009-0005-3887-5018","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, King Mongkut\u2019s University of Technology North Bangkok, Bangkok 10800, Thailand","institution_ids":["https://openalex.org/I82828225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5070023527"],"corresponding_institution_ids":["https://openalex.org/I82828225"],"apc_list":{"value":1800,"currency":"CHF","value_usd":2172},"apc_paid":{"value":1800,"currency":"CHF","value_usd":2172},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"11","first_page":"371","last_page":"371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9980000257492065,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9980000257492065,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.00019999999494757503,"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/T11019","display_name":"Image Enhancement Techniques","score":0.00019999999494757503,"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/adaptive-loss-weighting","display_name":"adaptive loss weighting","score":0.7540000081062317},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.9279999732971191},{"id":"https://openalex.org/keywords/pix2pix","display_name":"Pix2Pix","score":0.5730000138282776},{"id":"https://openalex.org/keywords/road-surface-reconstruction","display_name":"road surface reconstruction","score":0.414000004529953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6753000020980835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5554999709129333},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5393999814987183},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.4970000088214874},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42809998989105225},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.4027000069618225},{"id":"https://openalex.org/C2778090530","wikidata":"https://www.wikidata.org/wiki/Q2523931","display_name":"Viewport","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C193519340","wikidata":"https://www.wikidata.org/wiki/Q891179","display_name":"Data loss","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C2776821279","wikidata":"https://www.wikidata.org/wiki/Q2293902","display_name":"Mobile mapping","level":3,"score":0.3547999858856201},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C47431972","wikidata":"https://www.wikidata.org/wiki/Q3045948","display_name":"ELECTRE","level":3,"score":0.2994000017642975},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2736999988555908}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/make8110371","doi":"https://doi.org/10.3390/make8110371","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make8110371","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/make8110371","doi":"https://doi.org/10.3390/make8110371","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make8110371","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7222516671","https://openalex.org/W7160210618","https://openalex.org/W4400680806","https://openalex.org/W7220146138","https://openalex.org/W4308032615","https://openalex.org/W4391622958","https://openalex.org/W7224650133","https://openalex.org/W7160176759","https://openalex.org/W7168588508","https://openalex.org/W7221081016"],"abstract_inverted_index":{"Mobile":[0],"mapping":[1],"system":[2],"(MMS)":[3],"panoramas":[4,142],"routinely":[5],"capture":[6],"the":[7,16,20,57,86,92,128,137,178,226],"survey":[8],"vehicle,":[9],"which":[10,71],"occludes":[11],"a":[12,66,72,101,112,132],"substantial":[13],"portion":[14],"of":[15,30,229],"road":[17,32],"surface":[18],"beneath":[19],"camera.":[21],"Reconstructing":[22],"this":[23],"large":[24],"missing":[25],"region":[26,130],"is":[27,150],"challenging":[28],"because":[29],"complex":[31],"textures,":[33],"cast":[34],"shadows,":[35],"and":[36,96,99,109,135,145,156,163,167,194,199,222,240],"illumination":[37],"variations.":[38],"Although":[39],"GAN-based":[40],"inpainting":[41],"typically":[42],"combines":[43],"multiple":[44],"loss":[45,52,94,232],"terms":[46],"to":[47,56,187],"improve":[48],"reconstruction":[49,236],"quality,":[50],"fixed":[51],"weights":[53],"cannot":[54],"adapt":[55],"evolving":[58],"optimization":[59],"requirements":[60],"during":[61],"training.":[62],"This":[63],"study":[64],"proposes":[65],"quality-driven":[67],"loss-balancing":[68],"framework":[69,149],"in":[70,107],"Proximal":[73],"Policy":[74],"Optimization":[75],"(PPO)":[76],"controller":[77,87],"dynamically":[78],"adjusts":[79],"auxiliary-loss":[80],"weights.":[81],"At":[82],"each":[83],"control":[84],"step,":[85],"observes":[88],"interval-level":[89],"generator":[90],"losses,":[91],"current":[93],"weights,":[95],"training":[97,118,122,214],"progress,":[98],"receives":[100],"reward":[102],"derived":[103],"from":[104,140],"paired":[105],"improvements":[106,237],"SSIM":[108,206],"LPIPS":[110],"on":[111,158,201],"disjoint":[113],"controller-feedback":[114],"set.":[115],"Because":[116],"ground-truth":[117],"data":[119],"are":[120,124],"unavailable,":[121],"pairs":[123],"constructed":[125],"by":[126,196,207],"projecting":[127],"occluded":[129],"into":[131],"perspective":[133],"viewport":[134],"retrieving":[136],"corresponding":[138],"background":[139],"nearby":[141],"using":[143,165],"GPS":[144],"heading":[146],"information.":[147],"The":[148],"evaluated":[151],"against":[152],"Fixed-Weight":[153,188],"training,":[154,189],"SoftAdapt,":[155],"GradNorm":[157],"two":[159],"real-world":[160],"datasets,":[161],"MMS-Urban":[162],"MMS-Suburban,":[164],"Pix2Pix":[166,239],"Big-LaMa":[168],"backbones.":[169],"Experimental":[170],"results":[171],"show":[172],"that":[173],"PPO-guided":[174],"weight":[175],"adaptation":[176],"achieves":[177],"lowest":[179],"FID":[180,195],"across":[181],"all":[182],"four":[183],"backbone\u2013dataset":[184],"configurations.":[185],"Relative":[186],"it":[190],"reduces":[191],"LPIPS,":[192],"MAE,":[193],"14.80%,":[197],"15.64%,":[198],"20.65%":[200],"average,":[202],"respectively,":[203],"while":[204],"improving":[205],"4.08%,":[208],"with":[209,218,234],"less":[210],"than":[211],"1%":[212],"additional":[213,242],"time.":[215],"Further":[216],"comparisons":[217],"predefined":[219],"monotonic":[220],"scheduling":[221],"progress-only":[223],"PPO":[224],"demonstrate":[225],"backbone-dependent":[227],"contribution":[228],"state-informed":[230],"adaptive":[231],"balancing,":[233],"clearer":[235],"for":[238,244],"limited":[241],"benefits":[243],"Big-LaMa.":[245]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}