{"id":"https://openalex.org/W7166534635","doi":"https://doi.org/10.48550/arxiv.2606.27760","title":"PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion","display_name":"PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion","publication_year":2026,"publication_date":"2026-06-26","ids":{"openalex":"https://openalex.org/W7166534635","doi":"https://doi.org/10.48550/arxiv.2606.27760"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.27760","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27760","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.2606.27760","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139571832","display_name":"Zipeng Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Zipeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115598343","display_name":"Lichen Ma","orcid":"https://orcid.org/0000-0003-3817-2572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Lichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121999607","display_name":"Y He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123010257","display_name":"Xiaolong Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Xiaolong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135936066","display_name":"Jingling Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Jingling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006022044","display_name":"J W Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Junshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139553233","display_name":"Yan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yan","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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.4961000084877014,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.4961000084877014,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1257999986410141,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.08129999786615372,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/pixel","display_name":"Pixel","score":0.6177999973297119},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5712000131607056},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4690000116825104},{"id":"https://openalex.org/keywords/lossy-compression","display_name":"Lossy compression","score":0.4593000113964081},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.4368000030517578},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3977999985218048},{"id":"https://openalex.org/keywords/compression-artifact","display_name":"Compression artifact","score":0.38580000400543213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7002999782562256},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.6177999973297119},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5712000131607056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5051000118255615},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4690000116825104},{"id":"https://openalex.org/C165021410","wikidata":"https://www.wikidata.org/wiki/Q55564","display_name":"Lossy compression","level":2,"score":0.4593000113964081},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.4368000030517578},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43369999527931213},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.38580000400543213},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2865999937057495},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.27760","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27760","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.2606.27760","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.27760","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":[{"score":0.5102481245994568,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"pixel-space":[1,191],"diffusion":[2,203],"models":[3],"bypass":[4],"the":[5,53,62,123,164],"lossy":[6],"compression":[7],"of":[8,99,160,172,184],"Latent":[9],"Diffusion":[10,87],"Models":[11],"(LDMs)":[12],"but":[13],"struggle":[14],"to":[15,34,57,117,125],"jointly":[16],"model":[17],"low-frequency":[18,130,151],"semantics":[19],"and":[20,80,179,186,193],"high-frequency":[21,112],"signals":[22],"in":[23,97],"high-dimensional":[24],"space.":[25,92],"Existing":[26],"works":[27],"heavily":[28],"rely":[29],"on":[30,128],"complex":[31],"pixel":[32,91],"decoders":[33,49,96],"alleviate":[35],"this":[36,39,43,72,158],"issue.":[37],"In":[38],"paper,":[40],"we":[41,74,132],"challenge":[42],"trend":[44],"by":[45,71],"revealing":[46],"that":[47,108,157],"these":[48],"primarily":[50],"compensate":[51],"for":[52,76,90,201],"optimization":[54],"difficulties":[55],"inherent":[56],"velocity":[58],"prediction":[59],"($v$-prediction).":[60],"Under":[61],"clean":[63],"data":[64],"paradigm":[65,200],"($x$-prediction),":[66],"they":[67],"are":[68],"redundant.":[69],"Motivated":[70],"insight,":[73],"advocate":[75],"simplicity":[77],"over":[78],"complexity":[79],"introduce":[81,133],"PixelU,":[82],"a":[83,134,140,149,195],"minimalist,":[84],"single-stage":[85],"U-shaped":[86],"Transformer":[88],"tailored":[89],"PixelU":[93,181],"abandons":[94],"auxiliary":[95],"favor":[98],"zero-cost":[100],"skip":[101],"connections,":[102],"which":[103,144],"provide":[104],"an":[105],"\"information":[106],"highway\"":[107],"directly":[109],"routes":[110],"uncorrupted":[111],"spatial":[113,136],"details":[114],"from":[115],"shallow":[116],"deep":[118,146],"layers.":[119],"To":[120],"further":[121],"enable":[122],"backbone":[124],"focus":[126],"exclusively":[127],"modeling":[129],"semantics,":[131],"constant-channel":[135],"down-sampling":[137],"mechanism":[138],"as":[139],"natural":[141],"low-pass":[142],"filter,":[143],"compresses":[145],"features":[147],"into":[148],"compact,":[150],"semantic":[152],"manifold.":[153],"Extensive":[154],"experiments":[155],"demonstrate":[156],"decoupling":[159],"frequencies":[161],"could":[162],"outperform":[163],"strong":[165],"baseline":[166],"(JiT-G)":[167],"with":[168],"only":[169],"about":[170],"1/3":[171],"its":[173],"computation":[174],"cost.":[175],"On":[176],"ImageNet":[177],"256$\\times$256":[178],"512$\\times$512,":[180],"achieves":[182],"FID":[183],"1.63":[185],"1.92":[187],"respectively,":[188],"surpassing":[189],"recent":[190],"methods":[192],"establishing":[194],"simple":[196],"yet":[197],"powerful":[198],"new":[199],"end-to-end":[202],"models.":[204]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-30T00:00:00"}