{"id":"https://openalex.org/W7155180365","doi":"https://doi.org/10.48550/arxiv.2604.18790","title":"EfficientPENet: Real-Time Depth Completion from Sparse LiDAR via Lightweight Multi-Modal Fusion","display_name":"EfficientPENet: Real-Time Depth Completion from Sparse LiDAR via Lightweight Multi-Modal Fusion","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7155180365","doi":"https://doi.org/10.48550/arxiv.2604.18790"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.18790","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18790","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.18790","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134312382","display_name":"Johny J. Lopez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lopez, Johny J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134324209","display_name":"Md Meftahul Ferdaus","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ferdaus, Md Meftahul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134241744","display_name":"Mahdi Abdelguerfi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdelguerfi, Mahdi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055421257","display_name":"Anton Netchaev","orcid":"https://orcid.org/0000-0002-8463-1779"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Netchaev, Anton","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130369276","display_name":"Steven Sloan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sloan, Steven","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134253802","display_name":"Ken Pathak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pathak, Ken","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5093225472","display_name":"Kendall N. Niles","orcid":"https://orcid.org/0009-0007-2925-8856"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niles, Kendall N.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.637499988079071,"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":0.637499988079071,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.23229999840259552,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.030500000342726707,"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/lidar","display_name":"Lidar","score":0.5527999997138977},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.5202000141143799},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4945000112056732},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4560000002384186},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4237000048160553},{"id":"https://openalex.org/keywords/measured-depth","display_name":"Measured depth","score":0.4124000072479248},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.40389999747276306},{"id":"https://openalex.org/keywords/depth-map","display_name":"Depth map","score":0.38760000467300415},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.38339999318122864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387999892234802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6080999970436096},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5537999868392944},{"id":"https://openalex.org/C51399673","wikidata":"https://www.wikidata.org/wiki/Q504027","display_name":"Lidar","level":2,"score":0.5527999997138977},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.5202000141143799},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C113346285","wikidata":"https://www.wikidata.org/wiki/Q6804193","display_name":"Measured depth","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C141268832","wikidata":"https://www.wikidata.org/wiki/Q2940499","display_name":"Depth map","level":3,"score":0.38760000467300415},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32190001010894775},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C52672216","wikidata":"https://www.wikidata.org/wiki/Q1749840","display_name":"Depth perception","level":3,"score":0.30230000615119934},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.18790","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18790","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.18790","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18790","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":"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.43162280321121216}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Depth":[0],"completion":[1,47,136,189],"from":[2,95],"sparse":[3],"LiDAR":[4],"measurements":[5],"and":[6,67,90,103,148,166],"corresponding":[7],"RGB":[8,78],"images":[9],"is":[10],"a":[11,44,56,71,106,114,149,160,167,183],"prerequisite":[12],"for":[13,63,186],"accurate":[14],"3D":[15],"perception":[16],"in":[17,164],"robotic":[18],"systems.":[19],"Existing":[20],"methods":[21],"achieve":[22],"high":[23],"accuracy":[24],"on":[25,30,38,190],"standard":[26],"benchmarks":[27],"but":[28],"rely":[29],"heavy":[31],"backbone":[32],"architectures":[33],"that":[34,49,119],"preclude":[35],"real-time":[36,187],"deployment":[37],"embedded":[39],"hardware.":[40],"We":[41,111],"present":[42],"EfficientPENet,":[43],"two-branch":[45],"depth":[46,65,92,135,188],"network":[48],"replaces":[50],"the":[51,64,133,196],"conventional":[52],"ResNet":[53],"encoder":[54],"with":[55,84,145],"modernized":[57],"ConvNeXt":[58,82],"backbone,":[59],"introduces":[60],"sparsity-invariant":[61],"convolutions":[62],"stream,":[66],"refines":[68],"predictions":[69],"through":[70,105],"Convolutional":[72],"Spatial":[73],"Propagation":[74],"Network":[75],"(CSPN).":[76],"The":[77],"branch":[79],"leverages":[80],"ImageNet-pretrained":[81],"blocks":[83],"Layer":[85],"Normalization,":[86],"7x7":[87],"depthwise":[88],"convolutions,":[89],"stochastic":[91],"regularization.":[93],"Features":[94],"both":[96],"branches":[97],"are":[98],"merged":[99],"via":[100],"late":[101],"fusion":[102],"decoded":[104],"multi-scale":[107],"deep":[108],"supervision":[109],"strategy.":[110],"further":[112],"introduce":[113],"position-aware":[115],"test-time":[116],"augmentation":[117],"scheme":[118],"corrects":[120],"coordinate":[121],"tensors":[122],"during":[123],"horizontal":[124],"flipping,":[125],"yielding":[126],"consistent":[127],"error":[128],"reduction":[129,163],"at":[130,155],"inference.":[131],"On":[132],"KITTI":[134],"benchmark,":[137],"EfficientPENet":[138,181],"achieves":[139],"an":[140],"RMSE":[141],"of":[142,151],"631.94":[143],"mm":[144],"36.24M":[146],"parameters":[147,165],"latency":[150],"20.51":[152],"ms,":[153],"operating":[154],"48.76":[156],"FPS.":[157],"This":[158],"represents":[159],"3.7":[161],"times":[162,169],"23":[168],"speedup":[170],"relative":[171],"to":[172],"BP-Net,":[173],"while":[174],"maintaining":[175],"competitive":[176],"accuracy.":[177],"These":[178],"results":[179],"establish":[180],"as":[182,195],"practical":[184],"solution":[185],"resource-constrained":[191],"edge":[192],"platforms":[193],"such":[194],"NVIDIA":[197],"Jetson.":[198]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-23T00:00:00"}