{"id":"https://openalex.org/W4403788940","doi":"https://doi.org/10.48550/arxiv.2409.14365","title":"D3RoMa: Disparity Diffusion-based Depth Sensing for Material-Agnostic Robotic Manipulation","display_name":"D3RoMa: Disparity Diffusion-based Depth Sensing for Material-Agnostic Robotic Manipulation","publication_year":2024,"publication_date":"2024-09-22","ids":{"openalex":"https://openalex.org/W4403788940","doi":"https://doi.org/10.48550/arxiv.2409.14365"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2409.14365","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.14365","pdf_url":"https://arxiv.org/pdf/2409.14365","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.14365","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102822814","display_name":"Songlin Wei","orcid":"https://orcid.org/0000-0002-1487-1494","observed_orcids":["https://orcid.org/0000-0002-1487-1494"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Songlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101608437","display_name":"Haoran Geng","orcid":"https://orcid.org/0000-0001-8375-7196","observed_orcids":["https://orcid.org/0000-0001-8375-7196"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geng, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100609081","display_name":"Jiayi Chen","orcid":"https://orcid.org/0000-0002-5817-8317","observed_orcids":["https://orcid.org/0000-0002-5817-8317"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jiayi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050560702","display_name":"Congyue Deng","orcid":"https://orcid.org/0000-0002-0177-218X","observed_orcids":["https://orcid.org/0000-0002-0177-218X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Congyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069647397","display_name":"Wenbo Cui","orcid":"https://orcid.org/0000-0002-1000-4721","observed_orcids":["https://orcid.org/0000-0002-1000-4721"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Wenbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038866454","display_name":"Chengyang Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Chengyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Fang, Xiaomeng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Xiaomeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111954013","display_name":"Leonidas J. Guibas","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guibas, Leonidas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075606222","display_name":"He Wang","orcid":"https://orcid.org/0000-0002-3365-4620","observed_orcids":["https://orcid.org/0000-0002-3365-4620"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.9984999895095825,"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":0.9984999895095825,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.00019999999494757503,"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/depth-estimation","display_name":"depth estimation","score":0.8849999904632568},{"id":"https://openalex.org/keywords/stereo-vision","display_name":"stereo vision","score":0.7940000295639038},{"id":"https://openalex.org/keywords/denoising-diffusion-probabilistic-models","display_name":"denoising diffusion probabilistic models","score":0.9610000252723694},{"id":"https://openalex.org/keywords/image-to-image-translation","display_name":"image-to-image translation","score":0.7839999794960022},{"id":"https://openalex.org/keywords/classifier-guidance","display_name":"classifier guidance","score":0.8809999823570251},{"id":"https://openalex.org/keywords/specular-surfaces","display_name":"specular surfaces","score":0.9919999837875366},{"id":"https://openalex.org/keywords/synthetic-dataset","display_name":"synthetic dataset","score":0.6549999713897705},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.8270000219345093}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5096526145935059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4768558442592621},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.43511658906936646},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41537514328956604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41302186250686646},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.36673128604888916},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10764318704605103},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2409.14365","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.14365","pdf_url":"https://arxiv.org/pdf/2409.14365","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.14365","doi":"https://doi.org/10.48550/arxiv.2409.14365","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.14365","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.14365","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.14365","pdf_url":"https://arxiv.org/pdf/2409.14365","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Depth":[0],"sensing":[1,68],"is":[2,75],"an":[3,84],"important":[4],"problem":[5,87],"for":[6,148],"3D":[7],"vision-based":[8],"robotics.":[9],"Yet,":[10],"a":[11,35,94,105,135],"real-world":[12,160],"active":[13],"stereo":[14,41,128],"or":[15,62],"ToF":[16],"depth":[17,24,37,49,67,79,170,181],"camera":[18],"often":[19],"produces":[20],"noisy":[21],"and":[22,47,81,123,143,163],"incomplete":[23],"which":[25],"bottlenecks":[26],"robot":[27],"performances.":[28],"In":[29],"this":[30],"work,":[31],"we":[32,77,102,133],"propose":[33],"D3RoMa,":[34],"learning-based":[36,121],"estimation":[38,80,171],"framework":[39,117],"on":[40],"image":[42],"pairs":[43],"that":[44,76,179],"predicts":[45],"clean":[46],"accurate":[48,180],"in":[50,55,167,175,187],"diverse":[51,141],"indoor":[52],"scenes,":[53],"even":[54],"the":[56,90,113],"most":[57],"challenging":[58],"scenarios":[59],"with":[60,93,140],"translucent":[61],"specular":[63,144],"surfaces":[64],"where":[65],"classical":[66],"completely":[69],"fails.":[70],"Key":[71],"to":[72,112,146,159],"our":[73],"method":[74],"unify":[78],"restoration":[82],"into":[83],"image-to-image":[85],"translation":[86],"by":[88],"predicting":[89],"disparity":[91],"map":[92],"denoising":[95],"diffusion":[96,114],"probabilistic":[97],"model.":[98],"At":[99],"inference":[100],"time,":[101],"further":[103],"incorporated":[104],"left-right":[106],"consistency":[107],"constraint":[108],"as":[109],"classifier":[110],"guidance":[111],"process.":[115],"Our":[116],"combines":[118],"recently":[119],"advanced":[120],"approaches":[122],"geometric":[124],"constraints":[125],"from":[126],"traditional":[127],"vision.":[129],"For":[130],"model":[131,154],"training,":[132],"create":[134],"large":[136],"scene-level":[137],"synthetic":[138],"dataset":[139],"transparent":[142],"objects":[145],"compensate":[147],"existing":[149],"tabletop":[150],"datasets.":[151],"The":[152],"trained":[153],"can":[155],"be":[156],"directly":[157],"applied":[158],"in-the-wild":[161],"scenes":[162],"achieve":[164],"state-of-the-art":[165],"performance":[166],"multiple":[168],"public":[169],"benchmarks.":[172],"Further":[173],"experiments":[174],"real":[176],"environments":[177],"show":[178],"prediction":[182],"significantly":[183],"improves":[184],"robotic":[185],"manipulation":[186],"various":[188],"scenarios.":[189]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2024-10-27T00:00:00"}