{"id":"https://openalex.org/W4414433625","doi":"https://doi.org/10.1109/case58245.2025.11163793","title":"Unified Self-supervised Representation Learning for Multi-modal and Single-modal 3D Perception","display_name":"Unified Self-supervised Representation Learning for Multi-modal and Single-modal 3D Perception","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414433625","doi":"https://doi.org/10.1109/case58245.2025.11163793"},"language":"en","primary_location":{"id":"doi:10.1109/case58245.2025.11163793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018803784","display_name":"Xiaohao Xu","orcid":"https://orcid.org/0000-0002-6750-9704"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohao Xu","raw_affiliation_strings":["University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339214","display_name":"Ye Li","orcid":"https://orcid.org/0000-0002-2699-6630"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ye Li","raw_affiliation_strings":["University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437465","display_name":"Tianyi Zhang","orcid":"https://orcid.org/0009-0001-8703-0100"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Zhang","raw_affiliation_strings":["Carnegie Mellon University,Robotics Institute,Pittsburgh,PA,USA,15213"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101930120","display_name":"Jinrong Yang","orcid":"https://orcid.org/0000-0002-7678-0360"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinrong Yang","raw_affiliation_strings":["University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089990642","display_name":"Matthew Johnson\u2010Roberson","orcid":"https://orcid.org/0000-0002-0506-907X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Johnson-Roberson","raw_affiliation_strings":["Carnegie Mellon University,Robotics Institute,Pittsburgh,PA,USA,15213"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Robotics Institute,Pittsburgh,PA,USA,15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000690549","display_name":"Xiaonan Huang","orcid":"https://orcid.org/0000-0002-2313-1551"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaonan Huang","raw_affiliation_strings":["University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan,Robotics Department,Ann Arbor,MI,USA,48109","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"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":"2881","last_page":"2888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9957000017166138,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9957000017166138,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.988099992275238,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9869999885559082,"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/autoencoder","display_name":"Autoencoder","score":0.5946999788284302},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5788999795913696},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5396999716758728},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5013999938964844},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.499099999666214},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4986000061035156},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4805999994277954},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.47690001130104065}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7433000206947327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6833999752998352},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5946999788284302},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5788999795913696},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5013999938964844},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.47690001130104065},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.46459999680519104},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3978999853134155},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38190001249313354},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3001999855041504},{"id":"https://openalex.org/C28063669","wikidata":"https://www.wikidata.org/wiki/Q7167042","display_name":"Perceptual system","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C22033958","wikidata":"https://www.wikidata.org/wiki/Q7167036","display_name":"Perceptual learning","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case58245.2025.11163793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11163793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2150066425","https://openalex.org/W2963587345","https://openalex.org/W2963727135","https://openalex.org/W2968296999","https://openalex.org/W3034314779","https://openalex.org/W3035172746","https://openalex.org/W3035346742","https://openalex.org/W3035574168","https://openalex.org/W3108325989","https://openalex.org/W3109585842","https://openalex.org/W3118132944","https://openalex.org/W3167095230","https://openalex.org/W3167732492","https://openalex.org/W3172261075","https://openalex.org/W3173668541","https://openalex.org/W3176368002","https://openalex.org/W3203257492","https://openalex.org/W3204859697","https://openalex.org/W4200631318","https://openalex.org/W4225986494","https://openalex.org/W4237648096","https://openalex.org/W4312312750","https://openalex.org/W4312707458","https://openalex.org/W4312894406","https://openalex.org/W4312969460","https://openalex.org/W4313142137","https://openalex.org/W4313156423","https://openalex.org/W4319336452","https://openalex.org/W4383066393","https://openalex.org/W4383108631","https://openalex.org/W4386075756","https://openalex.org/W4386076357","https://openalex.org/W4386076702","https://openalex.org/W4390872476","https://openalex.org/W4393148991","https://openalex.org/W4394625645","https://openalex.org/W4396941548","https://openalex.org/W4401414023","https://openalex.org/W4401416341","https://openalex.org/W4401416408","https://openalex.org/W4404124919"],"related_works":[],"abstract_inverted_index":{"Constructing":[0],"large-scale":[1],"labeled":[2],"datasets":[3],"for":[4,15,26,49,95],"multi-modal":[5,37,88],"perception":[6,124],"in":[7,140],"autonomous":[8,96],"driving":[9,12],"is":[10,149],"challenging,":[11],"the":[13],"need":[14],"self-supervised":[16,113],"pretraining.":[17],"However,":[18],"existing":[19],"methods":[20,132],"typically":[21],"adopt":[22],"separate":[23,136],"pretraining":[24,47,131],"strategies":[25],"each":[27],"modality.":[28],"Inspired":[29],"by":[30],"Neural":[31],"Radiance":[32],"Field":[33],"(NeRF),":[34],"which":[35,133],"unifies":[36],"optimization,":[38],"we":[39],"propose":[40],"NeRF-Supervised":[41],"Masked":[42],"Autoencoder":[43],"(NS-MAE),":[44],"a":[45],"unified":[46],"strategy":[48],"LiDAR-Camera":[50],"3D":[51,123],"perception.":[52],"NS-MAE":[53,127],"encodes":[54],"both":[55],"appearance":[56],"and":[57,74,80,100],"geometry,":[58],"enabling":[59],"efficient":[60],"masked":[61],"reconstruction":[62,110],"across":[63,121],"modalities.":[64],"Specifically,":[65],"it":[66],"extracts":[67],"embeddings":[68,83],"from":[69,91],"corrupted":[70],"LiDAR":[71],"point":[72],"clouds":[73],"images,":[75],"conditioned":[76],"on":[77,135],"view":[78,99,102],"direction":[79],"location.":[81],"These":[82],"are":[84],"then":[85],"rendered":[86],"into":[87],"feature":[89],"maps":[90],"two":[92],"key":[93],"perspectives":[94],"driving:":[97],"perspective":[98],"bird\u2019s-eye":[101],"(BEV).":[103],"The":[104],"original":[105],"uncorrupted":[106],"data":[107],"serve":[108],"as":[109],"targets,":[111],"facilitating":[112],"learning.":[114],"Extensive":[115],"experiments":[116],"demonstrate":[117],"NS-MAE\u2019s":[118],"superior":[119],"transferability":[120],"various":[122],"tasks.":[125],"Notably,":[126],"outperforms":[128],"prior":[129],"SOTA":[130],"rely":[134],"modality-specific":[137],"strategies,":[138],"particularly":[139],"BEV":[141],"map":[142],"segmentation":[143],"under":[144],"label-efficient":[145],"fine-tuning.":[146],"Our":[147],"code":[148],"publicly":[150],"available":[151],"at":[152],"https://github.com/Xiaohao-Xu/Unified-Pretrain-AD/.":[153]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}