{"id":"https://openalex.org/W4387963763","doi":"https://doi.org/10.48550/arxiv.2310.16349","title":"DiffRef3D: A Diffusion-based Proposal Refinement Framework for 3D Object Detection","display_name":"DiffRef3D: A Diffusion-based Proposal Refinement Framework for 3D Object Detection","publication_year":2023,"publication_date":"2023-10-25","ids":{"openalex":"https://openalex.org/W4387963763","doi":"https://doi.org/10.48550/arxiv.2310.16349"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.16349","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.16349","pdf_url":"https://arxiv.org/pdf/2310.16349","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.16349","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101763186","display_name":"Se-Ho Kim","orcid":"https://orcid.org/0000-0002-3711-9473","observed_orcids":["https://orcid.org/0000-0002-3711-9473"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Se-Ho","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018771183","display_name":"Inyong Koo","orcid":"https://orcid.org/0000-0001-5366-1564","observed_orcids":["https://orcid.org/0000-0001-5366-1564"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Koo, Inyong","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lee, Inyoung","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Lee, Inyoung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051368302","display_name":"Byeongjun Park","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Park, Byeongjun","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069759184","display_name":"Changick Kim","orcid":"https://orcid.org/0000-0001-9323-8488","observed_orcids":["https://orcid.org/0000-0001-9323-8488"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Changick","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9452999830245972,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9452999830245972,"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":0.04320000112056732,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0010999999940395355,"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/3d-object-detection","display_name":"3D object detection","score":0.9549999833106995},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.7879999876022339},{"id":"https://openalex.org/keywords/proposal-refinement","display_name":"proposal refinement","score":0.8619999885559082},{"id":"https://openalex.org/keywords/point-clouds","display_name":"point clouds","score":0.9010000228881836},{"id":"https://openalex.org/keywords/conditional-diffusion","display_name":"conditional diffusion","score":0.6349999904632568},{"id":"https://openalex.org/keywords/two-stage-detectors","display_name":"two-stage detection","score":0.7379999756813049},{"id":"https://openalex.org/keywords/hypothesis-generation","display_name":"hypothesis generation","score":0.531000018119812},{"id":"https://openalex.org/keywords/kitti-dataset","display_name":"KITTI dataset","score":0.8140000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459105849266052},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6151449680328369},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6105417013168335},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5695136785507202},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5425629615783691},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49638015031814575},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4790952503681183},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4583004117012024},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45308202505111694},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3440036475658417},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10139688849449158},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.16349","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.16349","pdf_url":"https://arxiv.org/pdf/2310.16349","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.16349","doi":"https://doi.org/10.48550/arxiv.2310.16349","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.16349","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.16349","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.16349","pdf_url":"https://arxiv.org/pdf/2310.16349","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387963763.pdf","grobid_xml":"https://content.openalex.org/works/W4387963763.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W3092442149","https://openalex.org/W4379474799","https://openalex.org/W4379924367","https://openalex.org/W4390872147","https://openalex.org/W4390872929","https://openalex.org/W4390873752","https://openalex.org/W4390874574","https://openalex.org/W4392931179","https://openalex.org/W4393148069"],"related_works":["https://openalex.org/W4406166104","https://openalex.org/W4390144245","https://openalex.org/W3205005447","https://openalex.org/W3053706811","https://openalex.org/W4297833870","https://openalex.org/W6929649628","https://openalex.org/W2949708697","https://openalex.org/W4410551865","https://openalex.org/W4402754144","https://openalex.org/W4408714143"],"abstract_inverted_index":{"Denoising":[0],"diffusion":[1,32,60],"models":[2],"show":[3],"remarkable":[4],"performances":[5],"in":[6,13],"generative":[7],"tasks,":[8],"and":[9,73,97,119],"their":[10],"potential":[11],"applications":[12],"perception":[14],"tasks":[15],"are":[16],"gaining":[17],"interest.":[18],"In":[19,102],"this":[20],"paper,":[21],"we":[22,46],"introduce":[23],"a":[24,58,114,128],"novel":[25],"framework":[26,132],"named":[27],"DiffRef3D":[28,64,106,126,149],"which":[29],"adopts":[30],"the":[31,42,48,69,78,94,103,121,136,146,154],"process":[33],"on":[34,153],"3D":[35,54,140],"object":[36,55,141],"detection":[37,142],"with":[38],"point":[39],"clouds":[40],"for":[41],"first":[43],"time.":[44],"Specifically,":[45],"formulate":[47],"proposal":[49,130],"refinement":[50,87,131],"stage":[51],"of":[52,138,148],"two-stage":[53],"detectors":[56],"as":[57,117],"conditional":[59],"process.":[61],"During":[62],"training,":[63],"gradually":[65],"adds":[66],"noise":[67,112],"to":[68,81,83,92],"residuals":[70,80,96,118],"between":[71],"proposals":[72,82],"target":[74],"objects,":[75],"then":[76],"applies":[77],"noisy":[79,95],"generate":[84,98],"hypotheses.":[85],"The":[86],"module":[88],"utilizes":[89],"these":[90],"hypotheses":[91,109,122],"denoise":[93],"accurate":[99],"box":[100],"predictions.":[101],"inference":[104],"phase,":[105],"generates":[107],"initial":[108],"by":[110],"sampling":[111],"from":[113],"Gaussian":[115],"distribution":[116],"refines":[120],"through":[123,150],"iterative":[124],"steps.":[125],"is":[127],"versatile":[129],"that":[133],"consistently":[134],"improves":[135],"performance":[137],"existing":[139],"models.":[143],"We":[144],"demonstrate":[145],"significance":[147],"extensive":[151],"experiments":[152],"KITTI":[155],"benchmark.":[156],"Code":[157],"will":[158],"be":[159],"available.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2023-10-27T00:00:00"}