{"id":"https://openalex.org/W4411244561","doi":"https://doi.org/10.5244/c.35.86","title":"PS-Transformer: Learning Sparse Photometric Stereo Network using Self-Attention Mechanism","display_name":"PS-Transformer: Learning Sparse Photometric Stereo Network using Self-Attention Mechanism","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W4411244561","doi":"https://doi.org/10.5244/c.35.86"},"language":"en","primary_location":{"id":"doi:10.5244/c.35.86","doi":"https://doi.org/10.5244/c.35.86","is_oa":false,"landing_page_url":"https://doi.org/10.5244/c.35.86","pdf_url":null,"source":{"id":"https://openalex.org/S7407088578","display_name":"British Machine Vision Conference (BMVC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the British Machine Vision Conference 2021","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.11386","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069356829","display_name":"Satoshi Ikehata","orcid":"https://orcid.org/0000-0002-6061-7956","observed_orcids":["https://orcid.org/0000-0002-6061-7956"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Satoshi Ikehata","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5069356829"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6277,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.89653814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.38260000944137573,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.38260000944137573,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.3034999966621399,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.2703000009059906,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/self-attention","display_name":"self-attention","score":0.8379999995231628},{"id":"https://openalex.org/keywords/normal-estimation","display_name":"surface normal estimation","score":0.8960000276565552},{"id":"https://openalex.org/keywords/dual-branch-network","display_name":"dual-branch network","score":0.6869999766349792}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7163600921630859},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.584270715713501},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.48247030377388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4769900441169739},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33372431993484497},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13525548577308655},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13379651308059692},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1026138961315155},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.055773138999938965},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5244/c.35.86","doi":"https://doi.org/10.5244/c.35.86","is_oa":false,"landing_page_url":"https://doi.org/10.5244/c.35.86","pdf_url":null,"source":{"id":"https://openalex.org/S7407088578","display_name":"British Machine Vision Conference (BMVC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the British Machine Vision Conference 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2211.11386","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.11386","pdf_url":"https://arxiv.org/pdf/2211.11386","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2211.11386","doi":"https://doi.org/10.48550/arxiv.2211.11386","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.11386","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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.11386","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.11386","pdf_url":"https://arxiv.org/pdf/2211.11386","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411244561.pdf","grobid_xml":"https://content.openalex.org/works/W4411244561.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2899663614","https://openalex.org/W3003551007"],"related_works":["https://openalex.org/W3121558549","https://openalex.org/W3003300666","https://openalex.org/W4297239163","https://openalex.org/W2884608015","https://openalex.org/W3096595208","https://openalex.org/W4296986892","https://openalex.org/W2766067961","https://openalex.org/W4393235965","https://openalex.org/W2990635811","https://openalex.org/W4404442981"],"abstract_inverted_index":{"Existing":[0],"deep":[1,58],"calibrated":[2,60],"photometric":[3,61,125],"stereo":[4,62,126],"networks":[5],"basically":[6],"aggregate":[7],"observations":[8,43],"under":[9,44],"different":[10,48],"lights":[11],"based":[12],"on":[13,130],"the":[14,29,39,69,76,83,99,118,124,131,138,144,153],"pre-defined":[15],"operations":[16,34],"such":[17],"as":[18],"linear":[19],"projection":[20],"and":[21,90,93,159],"max":[22],"pooling.":[23],"While":[24],"they":[25],"are":[26],"effective":[27],"with":[28,98,117,152],"dense":[30,166],"capture,":[31],"simple":[32],"first-order":[33],"often":[35],"fail":[36],"to":[37,73,86,104,121,163],"capture":[38,75],"high-order":[40],"interactions":[41],"among":[42],"small":[45],"number":[46,155,172],"of":[47,143,156,165,173],"lights.":[49],"To":[50],"tackle":[51],"this":[52,54],"issue,":[53],"paper":[55],"presents":[56],"a":[57],"sparse":[59],"network":[63],"named":[64,112],"{\\it":[65],"PS-Transformer}":[66],"which":[67,168],"leverages":[68],"learnable":[70],"self-attention":[71],"mechanism":[72],"properly":[74],"complex":[77],"inter-image":[78],"interactions.":[79],"PS-Transformer":[80],"builds":[81],"upon":[82],"dual-branch":[84],"design":[85],"explore":[87],"both":[88],"pixel-wise":[89],"image-wise":[91],"features":[92],"individual":[94],"feature":[95],"is":[96,114,160],"trained":[97],"intermediate":[100],"surface":[101,139],"normal":[102,140],"supervision":[103],"maximize":[105],"geometric":[106],"feasibility.":[107],"A":[108],"new":[109],"synthetic":[110],"dataset":[111],"CyclesPS+":[113],"also":[115],"presented":[116],"comprehensive":[119],"analysis":[120],"successfully":[122],"train":[123],"networks.":[127],"Extensive":[128],"results":[129],"publicly":[132],"available":[133],"benchmark":[134],"datasets":[135],"demonstrate":[136],"that":[137,164],"prediction":[141],"accuracy":[142],"proposed":[145],"method":[146],"significantly":[147],"outperforms":[148],"other":[149],"state-of-the-art":[150],"algorithms":[151,167],"same":[154],"input":[157,169],"images":[158],"even":[161],"comparable":[162],"10$\\times$":[170],"larger":[171],"images.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":4}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}