{"id":"https://openalex.org/W7204200152","doi":"https://doi.org/10.48550/arxiv.2608.22821","title":"SiZeUp: Fast 3D Proxy from Aerial Images via Depth Ordinal Loss","display_name":"SiZeUp: Fast 3D Proxy from Aerial Images via Depth Ordinal Loss","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204200152","doi":"https://doi.org/10.48550/arxiv.2608.22821"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22821","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22821","pdf_url":"https://arxiv.org/pdf/2608.22821","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22821","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148082355","display_name":"Wenjun Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Wenjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129721170","display_name":"Yunshan Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yunshan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148086257","display_name":"Qiaoyu Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Qiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074153646","display_name":"Weidan Xiong","orcid":"https://orcid.org/0000-0001-5490-3676","observed_orcids":["https://orcid.org/0000-0001-5490-3676"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Weidan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397026","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0003-1991-119X","observed_orcids":["https://orcid.org/0000-0003-1991-119X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036688260","display_name":"Daniel Cohen\u2010Or","orcid":"https://orcid.org/0000-0001-6777-7445","observed_orcids":["https://orcid.org/0000-0001-6777-7445"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cohen-Or, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5148085098","display_name":"Hui Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Hui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.7080000042915344,"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"}},"topics":[{"id":"https://openalex.org/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.7080000042915344,"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/T12698","display_name":"3D Modeling in Geospatial Applications","score":0.08739999681711197,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.05810000002384186,"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/oblique-aerial-imagery","display_name":"oblique aerial photography","score":0.8140000104904175},{"id":"https://openalex.org/keywords/building-height-estimation","display_name":"building height estimation","score":0.8330000042915344},{"id":"https://openalex.org/keywords/differentiable-rendering","display_name":"differentiable rendering","score":0.8339999914169312},{"id":"https://openalex.org/keywords/monocular-depth-estimation","display_name":"monocular depth estimation","score":0.8019999861717224},{"id":"https://openalex.org/keywords/building-footprints","display_name":"building footprints","score":0.6420000195503235}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.571399986743927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5450999736785889},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.5386999845504761},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4489000141620636},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4424000084400177},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.4002000093460083},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3928000032901764},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35580000281333923},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3418000042438507},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C81386100","wikidata":"https://www.wikidata.org/wiki/Q7100792","display_name":"Ordinal optimization","level":3,"score":0.3285999894142151},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.3066999912261963},{"id":"https://openalex.org/C2778597888","wikidata":"https://www.wikidata.org/wiki/Q172169","display_name":"3D city models","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.2919999957084656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2776863239","wikidata":"https://www.wikidata.org/wiki/Q7936601","display_name":"Visual hull","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C158968445","wikidata":"https://www.wikidata.org/wiki/Q7631150","display_name":"Subgradient method","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2596000134944916},{"id":"https://openalex.org/C193581530","wikidata":"https://www.wikidata.org/wiki/Q683778","display_name":"Structured light","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22821","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22821","pdf_url":"https://arxiv.org/pdf/2608.22821","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22821","doi":"https://doi.org/10.48550/arxiv.2608.22821","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22821","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22821","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22821","pdf_url":"https://arxiv.org/pdf/2608.22821","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7250000238418579}],"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/W4394841776","https://openalex.org/W7135043775","https://openalex.org/W7170198919","https://openalex.org/W3085433944","https://openalex.org/W2519273726","https://openalex.org/W6903712545","https://openalex.org/W3107379492","https://openalex.org/W2887574725","https://openalex.org/W7117754438","https://openalex.org/W2148666178"],"abstract_inverted_index":{"We":[0],"present":[1],"SiZeUp,":[2],"a":[3,24,32,43,77,85,150,166],"fast":[4],"and":[5,50,72,116,179],"scalable":[6],"approach":[7,164],"for":[8,186],"constructing":[9],"large-scale":[10,187],"3D":[11,28],"urban":[12,188],"proxy":[13,171],"models":[14],"directly":[15],"from":[16,102],"calibrated":[17],"oblique":[18],"aerial":[19],"imagery.":[20],"Our":[21,108],"method":[22],"adopts":[23],"height-from-footprint":[25],"representation,":[26],"reducing":[27],"building":[29,38,91,106],"abstraction":[30],"to":[31,99,105],"low-dimensional":[33],"optimization":[34,113],"problem":[35],"in":[36,114],"which":[37,132],"footprints":[39],"are":[40],"extruded":[41],"by":[42,76],"single":[44],"height":[45,52],"parameter.":[46],"To":[47],"enable":[48],"efficient":[49,159],"robust":[51],"estimation,":[53],"we":[54],"introduce":[55],"an":[56,158],"ordinal":[57,109,141],"depth":[58,67,73,79,95,103,142],"consistency":[59,143],"loss":[60,144],"that":[61,88],"enforces":[62],"agreement":[63],"between":[64],"the":[65],"relative":[66,147],"ordering":[68],"of":[69],"rendered":[70],"proxies":[71,92],"priors":[74],"predicted":[75],"monocular":[78,137],"model.":[80],"This":[81],"is":[82],"realized":[83],"through":[84],"differentiable":[86],"renderer":[87],"maps":[89],"parametric":[90],"into":[93],"multi-view":[94],"images,":[96],"allowing":[97],"gradients":[98],"be":[100,134],"propagated":[101],"supervision":[104],"heights.":[107],"formulation":[110],"produces":[111],"stable":[112],"practice":[115],"avoids":[117],"explicit":[118],"feature":[119],"matching":[120],"or":[121],"dense":[122],"point":[123],"cloud":[124],"reconstruction.":[125],"Rather":[126],"than":[127],"relying":[128],"on":[129,146],"metric":[130],"depth,":[131],"can":[133],"unreliable":[135],"under":[136],"scale":[138],"ambiguity,":[139],"our":[140,163],"operates":[145],"depths,":[148],"providing":[149],"more":[151],"reliable":[152],"signal":[153],"across":[154],"views.":[155],"Combined":[156],"with":[157],"dynamic":[160],"view":[161],"selection,":[162],"achieves":[165],"23-52$\\times$":[167],"speedup":[168],"over":[169],"state-of-the-art":[170],"reconstruction":[172],"pipelines":[173],"while":[174],"maintaining":[175],"comparable":[176],"proxy-level":[177],"coverage":[178],"volume":[180],"consistency,":[181],"making":[182],"it":[183],"well":[184],"suited":[185],"modeling":[189],"tasks.":[190]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-08-26T00:00:00"}