{"id":"https://openalex.org/W7165685484","doi":"https://doi.org/10.48550/arxiv.2606.22749","title":"RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation","display_name":"RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation","publication_year":2026,"publication_date":"2026-06-22","ids":{"openalex":"https://openalex.org/W7165685484","doi":"https://doi.org/10.48550/arxiv.2606.22749"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.22749","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22749","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.22749","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049444390","display_name":"Yuchuan Ding","orcid":"https://orcid.org/0000-0001-5358-1660"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Yuchuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139184096","display_name":"Linfei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Linfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139162232","display_name":"Lin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139188334","display_name":"Ying Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Ying","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/T10036","display_name":"Advanced Neural Network Applications","score":0.37130001187324524,"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":0.37130001187324524,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.17399999499320984,"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":0.0851999968290329,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.7754999995231628},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.746399998664856},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5777000188827515},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5683000087738037},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48240000009536743},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.4523000121116638},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44429999589920044},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4341000020503998},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4187000095844269}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7754999995231628},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.746399998664856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6924999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985999703407288},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5777000188827515},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48240000009536743},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.4523000121116638},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44429999589920044},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4242999851703644},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3912999927997589},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3560999929904938},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.32359999418258667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3075999915599823},{"id":"https://openalex.org/C101814296","wikidata":"https://www.wikidata.org/wiki/Q5439685","display_name":"Feature model","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C32990609","wikidata":"https://www.wikidata.org/wiki/Q306542","display_name":"Transformation geometry","level":2,"score":0.26420000195503235}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.22749","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22749","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.22749","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22749","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Pre-trained":[0],"Vision":[1],"Foundation":[2],"Models":[3],"(VFMs)":[4],"have":[5],"become":[6],"central":[7],"to":[8,13],"modern":[9],"computer":[10],"vision":[11],"due":[12],"their":[14,23,32],"powerful":[15],"semantic":[16,46],"representations":[17],"and":[18,53,58,70,118,173,187,193],"strong":[19],"generalization":[20],"ability.":[21],"However,":[22],"patchified":[24],"or":[25,48,87],"pooled":[26],"outputs":[27],"are":[28],"inherently":[29],"low-resolution,":[30],"limiting":[31],"effectiveness":[33],"in":[34],"tasks":[35,157],"requiring":[36],"fine-grained,":[37],"pixel-level":[38],"reasoning.":[39],"Existing":[40],"feature":[41,72,78,92,198],"upsampling":[42,73],"approaches":[43],"either":[44],"degrade":[45],"fidelity":[47],"rely":[49],"on":[50],"VFM-specific":[51],"retraining":[52],"heavy":[54],"architectures,":[55],"hindering":[56],"efficiency":[57],"scalability.":[59],"To":[60],"address":[61],"these":[62],"challenges,":[63],"we":[64,100],"propose":[65],"RaysUp,":[66],"an":[67,111],"ultra-lightweight,":[68],"task-agnostic,":[69],"VFM-agnostic":[71],"framework":[74],"that":[75,125,159],"reconstructs":[76],"high-resolution":[77],"maps":[79],"at":[80,203],"arbitrary":[81],"resolutions.":[82],"Unlike":[83],"conventional":[84],"2D":[85],"interpolation":[86],"attention-based":[88],"schemes,":[89],"RaysUp":[90,160,189],"lifts":[91],"reconstruction":[93],"into":[94],"a":[95,102,119,137,182,191],"geometry-aware":[96],"ray":[97,134],"domain.":[98],"Specifically,":[99],"introduce":[101],"Spatially":[103],"Decoupled":[104],"Guidance":[105],"Encoder":[106],"for":[107,115,196],"direction-aware":[108],"guidance":[109],"encoding,":[110],"Any-Resolution":[112],"Cross-Attention":[113],"mechanism":[114],"resolution-flexible":[116],"reconstruction,":[117],"novel":[120],"Ray":[121],"Positional":[122],"Encoding":[123],"(RayPE)":[124],"injects":[126],"implicit":[127],"3D":[128],"geometric":[129,149],"priors":[130],"via":[131],"6D":[132],"Plucker":[133],"coordinates.":[135],"Finally,":[136],"Geometry-Aware":[138],"Neighborhood":[139],"Attention":[140],"module":[141],"further":[142],"ensures":[143],"content-adaptive":[144],"bilateral":[145],"aggregation":[146],"while":[147,164],"preserving":[148],"consistency.":[150],"Extensive":[151],"experiments":[152],"across":[153],"diverse":[154],"dense":[155],"prediction":[156],"demonstrate":[158],"achieves":[161],"state-of-the-art":[162],"performance":[163],"using":[165],"only":[166],"16%":[167],"of":[168,171],"the":[169],"parameters":[170],"AnyUp":[172],"delivering":[174],"approximately":[175],"7x":[176],"faster":[177],"inference.":[178],"These":[179],"results":[180],"highlight":[181],"substantially":[183],"improved":[184],"accuracy-efficiency":[185],"trade-off":[186],"establish":[188],"as":[190],"practical":[192],"scalable":[194],"solution":[195],"universal":[197],"upsampling.":[199],"Code":[200],"is":[201],"available":[202],"https://github.com/MAP-RaysUp/RaysUp.":[204]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}