{"id":"https://openalex.org/W7162528108","doi":"https://doi.org/10.1109/3dv69130.2026.00011","title":"L4P: Towards Unified Low-Level 4D Vision Perception","display_name":"L4P: Towards Unified Low-Level 4D Vision Perception","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W7162528108","doi":"https://doi.org/10.1109/3dv69130.2026.00011"},"language":null,"primary_location":{"id":"doi:10.1109/3dv69130.2026.00011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","raw_type":"proceedings-article"},"type":"article","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/A5068825618","display_name":"Abhishek Badki","orcid":"https://orcid.org/0000-0002-5559-2336"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhishek Badki","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137162829","display_name":"Hang Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hang Su","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003458289","display_name":"Bowen Wen","orcid":"https://orcid.org/0000-0002-9207-6103"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowen Wen","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023093138","display_name":"Orazio Gallo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Orazio Gallo","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85350001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.3230000138282776,"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":0.3230000138282776,"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":0.093299999833107,"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/T11019","display_name":"Image Enhancement Techniques","score":0.08619999885559082,"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/perception","display_name":"Perception","score":0.4999000132083893},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.32600000500679016},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.304500013589859},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.2897000014781952}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.49470001459121704},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.43700000643730164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4002000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34540000557899475},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/3dv69130.2026.00011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3dv69130.2026.00011","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on 3D Vision (3DV)","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":69,"referenced_works":["https://openalex.org/W1513100184","https://openalex.org/W1907877624","https://openalex.org/W2129404737","https://openalex.org/W2156598602","https://openalex.org/W2169887425","https://openalex.org/W2205172244","https://openalex.org/W2215643317","https://openalex.org/W2259424905","https://openalex.org/W2471962767","https://openalex.org/W2519683295","https://openalex.org/W2566030665","https://openalex.org/W2610147486","https://openalex.org/W2894983388","https://openalex.org/W2912857574","https://openalex.org/W2955639361","https://openalex.org/W2962793285","https://openalex.org/W2962989121","https://openalex.org/W2963782415","https://openalex.org/W2963983744","https://openalex.org/W2964153986","https://openalex.org/W3035172746","https://openalex.org/W3048510980","https://openalex.org/W3109908659","https://openalex.org/W3132270109","https://openalex.org/W3174522583","https://openalex.org/W3174541782","https://openalex.org/W4214520160","https://openalex.org/W4221167977","https://openalex.org/W4312326540","https://openalex.org/W4312339971","https://openalex.org/W4312601813","https://openalex.org/W4313156423","https://openalex.org/W4385259380","https://openalex.org/W4386057769","https://openalex.org/W4386066345","https://openalex.org/W4386072148","https://openalex.org/W4390871746","https://openalex.org/W4390871749","https://openalex.org/W4390871809","https://openalex.org/W4390872625","https://openalex.org/W4390872749","https://openalex.org/W4390872949","https://openalex.org/W4390874416","https://openalex.org/W4390874575","https://openalex.org/W4402354026","https://openalex.org/W4402716510","https://openalex.org/W4402727359","https://openalex.org/W4402728154","https://openalex.org/W4402753851","https://openalex.org/W4402753888","https://openalex.org/W4402816534","https://openalex.org/W4403888324","https://openalex.org/W4403906568","https://openalex.org/W4404002617","https://openalex.org/W4409366496","https://openalex.org/W4413145609","https://openalex.org/W4413146238","https://openalex.org/W4413147631","https://openalex.org/W4413147750","https://openalex.org/W4413147840","https://openalex.org/W4413155739","https://openalex.org/W4413155845","https://openalex.org/W4413556455","https://openalex.org/W7108068597","https://openalex.org/W7133182943","https://openalex.org/W7133185381","https://openalex.org/W7133229819","https://openalex.org/W7133239857","https://openalex.org/W7160058165"],"related_works":[],"abstract_inverted_index":{"The":[0],"spatio-temporal":[1],"relationship":[2],"between":[3],"the":[4,42],"pixels":[5],"of":[6,131],"a":[7,49,60,65,126],"video":[8,68],"carries":[9],"critical":[10],"information":[11],"for":[12,41],"low-level":[13,55],"4D":[14,56],"perception":[15,57],"tasks.":[16],"A":[17],"single":[18],"model":[19],"that":[20,53,76,130],"reasons":[21],"about":[22],"it":[23,72,119],"should":[24],"be":[25],"able":[26],"to":[27,129],"solve":[28],"several":[29],"such":[30,104,114],"tasks":[31,58,122],"well.":[32],"Yet,":[33],"most":[34],"state-of-theart":[35],"methods":[36,99],"rely":[37],"on":[38,100],"architectures":[39],"specialized":[40,98],"task":[43],"at":[44,123],"hand.":[45],"We":[46],"present":[47],"L4P,":[48],"feedforward,":[50],"general-purpose":[51],"architecture":[52],"solves":[54,120],"in":[59,125],"unified":[61],"framework.":[62],"LAP":[63],"leverages":[64],"pre-trained":[66],"ViT-based":[67],"encoder":[69],"and":[70,79,89,111],"combines":[71],"with":[73,96],"per-task":[74],"heads":[75],"are":[77],"lightweight":[78],"therefore":[80],"do":[81],"not":[82],"require":[83],"extensive":[84],"training.":[85],"Despite":[86],"its":[87],"general":[88],"feedforward":[90],"formulation,":[91],"our":[92],"method":[93],"is":[94],"competitive":[95],"existing":[97],"both":[101],"dense":[102],"tasks,":[103,113],"as":[105,115],"depth":[106],"or":[107],"optical":[108],"flow":[109],"estimation,":[110],"sparse":[112],"2D/3D":[116],"tracking.":[117],"Moreover,":[118],"all":[121],"once":[124],"time":[127],"comparable":[128],"single-task":[132],"methods.":[133]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-28T00:00:00"}