{"id":"https://openalex.org/W4414690267","doi":"https://doi.org/10.1109/iccv51701.2025.02427","title":"Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning","display_name":"Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414690267","doi":"https://doi.org/10.1109/iccv51701.2025.02427"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.09102","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087811347","display_name":"Yiyang Chen","orcid":"https://orcid.org/0000-0001-9960-9040"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyang Chen","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114860317","display_name":"Shanshan Zhao","orcid":"https://orcid.org/0009-0009-5523-8407"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shanshan Zhao","raw_affiliation_strings":["Alibaba International Digital Commerce Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017333360","display_name":"Lunhao Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lunhao Duan","raw_affiliation_strings":["Alibaba International Digital Commerce Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038748720","display_name":"Changxing Ding","orcid":"https://orcid.org/0000-0001-7232-3181"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changxing Ding","raw_affiliation_strings":["South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033000556","display_name":"Dacheng Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"26156","last_page":"26166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.866100013256073,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.866100013256073,"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":0.8384000062942505,"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/point-cloud","display_name":"Point cloud","score":0.8169000148773193},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5146999955177307},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5047000050544739},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5026000142097473},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5023000240325928},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49059998989105225},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.47749999165534973}],"concepts":[{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.8169000148773193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7171000242233276},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5146999955177307},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5047000050544739},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5026000142097473},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5023000240325928},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49059998989105225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48910000920295715},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.36070001125335693},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35530000925064087},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.35350000858306885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3458000123500824},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3345000147819519},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.328000009059906},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.09102","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.09102","pdf_url":"https://arxiv.org/pdf/2507.09102","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.09102","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.09102","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.09102","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.09102","pdf_url":"https://arxiv.org/pdf/2507.09102","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5275746567","display_name":null,"funder_award_id":"2024B1515020082,2023A1515010007","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6485948635","display_name":null,"funder_award_id":"62476099,62076101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion-based":[0],"models,":[1,64],"widely":[2],"used":[3],"in":[4,10],"text-to-image":[5,62],"generation,":[6],"have":[7],"proven":[8],"effective":[9],"2D":[11],"representation":[12],"learning.":[13,97,168,189],"Recently,":[14],"this":[15,82],"framework":[16,88],"has":[17],"been":[18],"extended":[19],"to":[20,119,146],"3D":[21,32,41,50,95,107,154],"self-supervised":[22,96,188],"learning":[23],"by":[24,39,156],"constructing":[25],"a":[26,87,106,111,153],"conditional":[27],"point":[28,117,141,173,186],"generator":[29],"for":[30,94],"enhancing":[31],"representations.":[33],"However,":[34],"its":[35,158],"performance":[36],"remains":[37],"constrained":[38],"the":[40,48,58,91,100,121,128,138,144,181],"diffusion":[42,63,113,131],"model,":[43,132],"which":[44,69],"is":[45,70,191],"trained":[46,71,129],"on":[47,72,171],"available":[49,193],"datasets":[51],"with":[52,105,160],"limited":[53],"size.":[54],"We":[55],"hypothesize":[56],"that":[57,89,115,180],"robust":[59],"capabilities":[60],"of":[61,123],"particularly":[65],"Stable":[66],"Diffusion":[67],"(SD),":[68],"large-scale":[73],"datasets,":[74],"can":[75,184],"help":[76],"overcome":[77],"these":[78,161],"limitations.":[79],"To":[80],"investigate":[81],"hypothesis,":[83],"we":[84,109,133,151],"propose":[85],"PointSD,":[86],"leverages":[90],"SD":[92,101,148,162,182],"model":[93,114,183],"By":[98],"replacing":[99],"model's":[102],"text":[103],"encoder":[104],"encoder,":[108],"train":[110,152],"point-to-image":[112,130],"allows":[116],"clouds":[118,142],"guide":[120],"denoising":[122],"rendered":[124],"noisy":[125],"images.":[126],"With":[127],"use":[134],"noise-free":[135],"images":[136],"as":[137,143],"input":[139],"and":[140,176],"condition":[145],"extract":[147],"features.":[149],"Next,":[150],"backbone":[155],"aligning":[157],"features":[159],"features,":[163],"thereby":[164],"facilitating":[165],"direct":[166],"semantic":[167],"Comprehensive":[169],"experiments":[170],"downstream":[172],"cloud":[174,187],"tasks":[175],"ablation":[177],"studies":[178],"demonstrate":[179],"enhance":[185],"Code":[190],"publicly":[192],"at":[194],"https://github.com/wdttt/PointSD.":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}