{"id":"https://openalex.org/W4416442992","doi":"https://doi.org/10.1109/wacv61042.2026.00138","title":"GrounDiff: Diffusion-Based Ground Surface Generation from Digital Surface Models","display_name":"GrounDiff: Diffusion-Based Ground Surface Generation from Digital Surface Models","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416442992","doi":"https://doi.org/10.1109/wacv61042.2026.00138"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.10391","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054428785","display_name":"Oussema Dhaouadi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087778","display_name":"Dascena (United States)","ror":"https://ror.org/002g7k102","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087778"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Oussema Dhaouadi","raw_affiliation_strings":["DeepScenario"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepScenario","institution_ids":["https://openalex.org/I4210087778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046390826","display_name":"J. Meier","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087778","display_name":"Dascena (United States)","ror":"https://ror.org/002g7k102","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Johannes Meier","raw_affiliation_strings":["DeepScenario"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepScenario","institution_ids":["https://openalex.org/I4210087778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028490309","display_name":"Jacques Kaiser","orcid":"https://orcid.org/0000-0001-7487-6185"},"institutions":[{"id":"https://openalex.org/I4210087778","display_name":"Dascena (United States)","ror":"https://ror.org/002g7k102","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacques Kaiser","raw_affiliation_strings":["DeepScenario"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepScenario","institution_ids":["https://openalex.org/I4210087778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087710605","display_name":"Daniel Cremers","orcid":"https://orcid.org/0000-0002-3079-7984"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Cremers","raw_affiliation_strings":["TU Munich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Munich","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054428785"],"corresponding_institution_ids":["https://openalex.org/I4210087778"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00190663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1355","last_page":"1364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.8425999879837036,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.8425999879837036,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.04729999974370003,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.01769999973475933,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image-stitching","display_name":"Image stitching","score":0.786300003528595},{"id":"https://openalex.org/keywords/digital-elevation-model","display_name":"Digital elevation model","score":0.6722000241279602},{"id":"https://openalex.org/keywords/terrain","display_name":"Terrain","score":0.5857999920845032},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5214999914169312},{"id":"https://openalex.org/keywords/geospatial-analysis","display_name":"Geospatial analysis","score":0.46299999952316284},{"id":"https://openalex.org/keywords/smoothness","display_name":"Smoothness","score":0.4336000084877014},{"id":"https://openalex.org/keywords/lidar","display_name":"Lidar","score":0.420199990272522},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.40310001373291016},{"id":"https://openalex.org/keywords/surface","display_name":"Surface (topology)","score":0.396699994802475}],"concepts":[{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.786300003528595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.679099977016449},{"id":"https://openalex.org/C181843262","wikidata":"https://www.wikidata.org/wiki/Q640492","display_name":"Digital elevation model","level":2,"score":0.6722000241279602},{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.5857999920845032},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5214999914169312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5023000240325928},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C102634674","wikidata":"https://www.wikidata.org/wiki/Q868473","display_name":"Smoothness","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.4287000000476837},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C2776799497","wikidata":"https://www.wikidata.org/wiki/Q484298","display_name":"Surface (topology)","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39430001378059387},{"id":"https://openalex.org/C181672929","wikidata":"https://www.wikidata.org/wiki/Q4115141","display_name":"Digital mapping","level":2,"score":0.38839998841285706},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3709000051021576},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.34709998965263367},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33000001311302185},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C37054046","wikidata":"https://www.wikidata.org/wiki/Q641888","display_name":"Elevation (ballistics)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C2983128922","wikidata":"https://www.wikidata.org/wiki/Q1789829","display_name":"Digital surface","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C99695388","wikidata":"https://www.wikidata.org/wiki/Q350514","display_name":"Raised-relief map","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2687000036239624},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C117455697","wikidata":"https://www.wikidata.org/wiki/Q190149","display_name":"Photogrammetry","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.10391","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.10391","pdf_url":"https://arxiv.org/pdf/2511.10391","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2511.10391","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.10391","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.10391","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.10391","pdf_url":"https://arxiv.org/pdf/2511.10391","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Digital":[0,29],"Terrain":[1],"Models":[2,31],"(DTMs)":[3],"represent":[4],"the":[5,65,76,123,155,181],"bare-earth":[6],"elevation":[7],"and":[8,24,147,165],"are":[9,25],"important":[10],"in":[11],"numerous":[12],"geospatial":[13],"applications.":[14],"Such":[15],"data":[16],"models":[17],"cannot":[18],"be":[19],"directly":[20],"measured":[21],"by":[22,74,141],"sensors":[23],"typically":[26],"generated":[27,110],"from":[28,34],"Surface":[30],"(DSMs)":[32],"derived":[33],"LiDAR":[35],"or":[36],"photogrammetry.":[37],"Traditional":[38],"filtering":[39],"approaches":[40],"rely":[41],"on":[42,122,145,151,180],"manually":[43],"tuned":[44],"parameters,":[45],"while":[46,184],"learning-based":[47,136],"methods":[48],"require":[49],"well-designed":[50],"architectures,":[51],"often":[52],"combined":[53],"with":[54,87],"post-processing.":[55],"To":[56,94],"address":[57],"these":[58],"challenges,":[59],"we":[60,97],"introduce":[61],"Ground":[62],"Diffusion":[63],"(GrounDiff),":[64],"first":[66],"diffusion-based":[67],"framework":[68],"that":[69,90,131],"iteratively":[70],"removes":[71],"non-ground":[72],"structures":[73],"formulating":[75],"problem":[77],"as":[78],"a":[79,84,105],"denoising":[80],"task.":[81],"We":[82,118],"incorporate":[83],"gated":[85],"design":[86],"confidence-guided":[88],"generation":[89],"enables":[91],"selective":[92],"filtering.":[93],"increase":[95],"scalability,":[96],"further":[98,210],"propose":[99],"Prior-Guided":[100],"Stitching":[101],"(PrioStitch),":[102],"which":[103,160],"employs":[104],"downsampled":[106],"global":[107],"prior":[108],"automatically":[109],"using":[111,189],"GrounDiff":[112,132],"to":[113,143,149,171,177,205],"guide":[114],"local":[115],"high-resolution":[116],"predictions.":[117],"evaluate":[119],"our":[120,167],"method":[121,168],"DSM-to-DTM":[124],"translation":[125],"task":[126,156],"across":[127],"diverse":[128],"datasets,":[129],"showing":[130],"consistently":[133],"outperforms":[134],"deep":[135],"state-of-the-art":[137,212],"methods,":[138],"reducing":[139],"RMSE":[140],"up":[142,148,170],"93%":[144],"ALS2DTM":[146],"47%":[150],"USGS":[152],"benchmarks.":[153],"In":[154],"of":[157],"road":[158,199],"reconstruction,":[159,200],"requires":[161],"both":[162],"high":[163],"precision":[164],"smoothness,":[166],"achieves":[169],"81%":[172],"lower":[173],"distance":[174],"error":[175],"compared":[176],"specialized":[178],"techniques":[179],"GeRoD":[182],"benchmark,":[183],"maintaining":[185],"competitive":[186],"surface":[187],"smoothness":[188],"only":[190],"DSM":[191],"inputs,":[192],"without":[193],"task-specific":[194],"optimization.":[195],"Our":[196],"variant":[197],"for":[198],"GrounDiff+,":[201],"is":[202,217],"specifically":[203],"designed":[204],"produce":[206],"even":[207],"smoother":[208],"surfaces,":[209],"surpassing":[211],"methods.":[213],"The":[214],"project":[215],"page":[216],"available":[218],"at":[219],"https://deepscenario.github.io/GrounDiff/.":[220]},"counts_by_year":[],"updated_date":"2026-05-07T06:04:25.777469","created_date":"2025-11-15T00:00:00"}