{"id":"https://openalex.org/W7204194823","doi":"https://doi.org/10.48550/arxiv.2608.21885","title":"Pixel-Space Diffusion via Observation Operators","display_name":"Pixel-Space Diffusion via Observation Operators","publication_year":2026,"publication_date":"2026-08-22","ids":{"openalex":"https://openalex.org/W7204194823","doi":"https://doi.org/10.48550/arxiv.2608.21885"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.21885","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21885","pdf_url":"https://arxiv.org/pdf/2608.21885","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","license_id":"https://openalex.org/licenses/cc-by","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/2608.21885","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147385572","display_name":"Shaojie Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Shaojie","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115598343","display_name":"Lichen Ma","orcid":"https://orcid.org/0000-0003-3817-2572","observed_orcids":["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/A5129749748","display_name":"Haoyang Tong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong, Haoyang","raw_affiliation_strings":["JD.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147389220","display_name":"Yu He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He, Yu","raw_affiliation_strings":["JD.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136472917","display_name":"Zipeng Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Zipeng","raw_affiliation_strings":["JD.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133127578","display_name":"Xiaoan Liu","orcid":"https://orcid.org/0009-0005-1294-7108","observed_orcids":["https://orcid.org/0009-0005-1294-7108"]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Xiaoan","raw_affiliation_strings":["JD.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133377003","display_name":"Feng Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan, Feng","raw_affiliation_strings":["JD.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122925752","display_name":"Yu Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Yu","raw_affiliation_strings":["JD.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148121926","display_name":"Fei Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Fei","raw_affiliation_strings":["JD.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123009681","display_name":"Junshi Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Junshi","raw_affiliation_strings":["JD.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD.com","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148078644","display_name":"Yan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yan","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9491999745368958,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9491999745368958,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.04610000178217888,"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":0.0007999999797903001,"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/observation-operator","display_name":"observation operator","score":0.7110000252723694},{"id":"https://openalex.org/keywords/image-denoising","display_name":"image denoising","score":0.5960000157356262},{"id":"https://openalex.org/keywords/image-generation","display_name":"image generation","score":0.5649999976158142}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7569000124931335},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6527000069618225},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6136999726295471},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5393000245094299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5335000157356262},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5146999955177307},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5109000205993652},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5052000284194946},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3953999876976013},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3546000123023987},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3321000039577484},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.2870999872684479},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C35772409","wikidata":"https://www.wikidata.org/wiki/Q1323086","display_name":"Image noise","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.26759999990463257},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.21885","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21885","pdf_url":"https://arxiv.org/pdf/2608.21885","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.21885","doi":"https://doi.org/10.48550/arxiv.2608.21885","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.21885","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.21885","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21885","pdf_url":"https://arxiv.org/pdf/2608.21885","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","license_id":"https://openalex.org/licenses/cc-by","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/W7204194823.pdf","grobid_xml":"https://content.openalex.org/works/W7204194823.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7214056667","https://openalex.org/W7203683216","https://openalex.org/W7206168257","https://openalex.org/W7106694720","https://openalex.org/W4402716213","https://openalex.org/W7164904055","https://openalex.org/W7106789420","https://openalex.org/W7222974185","https://openalex.org/W7221782987","https://openalex.org/W7127275266"],"abstract_inverted_index":{"Pixel-space":[0],"diffusion":[1],"models":[2,51],"directly":[3],"model":[4],"image":[5,38,58,97,123],"distributions":[6],"but":[7],"remain":[8],"difficult":[9],"to":[10,44,54,120],"optimize.":[11],"Recent":[12],"methods":[13],"alleviate":[14],"this":[15,72],"challenge":[16],"through":[17],"target":[18,27],"reparameterization,":[19],"while":[20,173],"still":[21],"relying":[22],"on":[23,183],"a":[24,35,79,111,131,141,149],"fixed":[25,102],"clean-image":[26],"throughout":[28],"denoising.":[29,125],"Through":[30],"empirical":[31],"analysis,":[32],"we":[33,74,100],"identify":[34],"scale-time":[36],"mismatch:":[37],"structures":[39,119],"become":[40],"predictable":[41],"from":[42,117],"coarse":[43,118],"fine":[45],"as":[46],"noise":[47],"decreases,":[48],"whereas":[49],"existing":[50],"are":[52],"forced":[53],"predict":[55],"the":[56,85,92,106,121,167],"full":[57,122],"even":[59],"under":[60],"high":[61],"noise,":[62],"resulting":[63],"in":[64],"low-SNR":[65],"gradients":[66],"that":[67,82,115,151,166],"hinder":[68],"optimization.":[69],"To":[70],"resolve":[71],"mismatch,":[73],"propose":[75],"Observation":[76],"Operator":[77],"Diffusion,":[78],"unified":[80],"framework":[81],"aligns":[83],"both":[84],"supervision":[86,104],"trajectory":[87,114,127],"and":[88],"feature":[89,161],"refinement":[90],"with":[91,110,130],"intrinsic":[93],"recovery":[94],"order":[95],"of":[96,133,181],"structures.":[98],"Specifically,":[99],"replace":[101],"full-image":[103],"along":[105],"standard":[107],"flow":[108],"path":[109],"time-indexed":[112],"observation":[113,138],"evolves":[116],"during":[124],"This":[126],"is":[128],"instantiated":[129],"family":[132],"Gaussian-Lanczos":[134,154],"operators":[135],"at":[136],"varying":[137],"scales,":[139],"yielding":[140],"path-consistent":[142],"training":[143],"objective.":[144],"We":[145],"further":[146],"introduce":[147],"GL-CoDA,":[148],"decoder":[150],"injects":[152],"scale-specific":[153],"observations":[155],"across":[156],"decoding":[157],"stages":[158],"for":[159],"coarse-to-fine":[160],"refinement.":[162],"Extensive":[163],"experiments":[164],"show":[165],"proposed":[168],"approach":[169],"converges":[170],"substantially":[171],"faster":[172],"consistently":[174],"improving":[175],"generation":[176],"quality,":[177],"achieving":[178],"an":[179],"FID":[180],"1.52":[182],"ImageNet-256.":[184]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}