{"id":"https://openalex.org/W7152033302","doi":"https://doi.org/10.48550/arxiv.2604.06074","title":"Graph-PiT: Enhancing Structural Coherence in Part-Based Image Synthesis via Graph Priors","display_name":"Graph-PiT: Enhancing Structural Coherence in Part-Based Image Synthesis via Graph Priors","publication_year":2026,"publication_date":"2026-04-07","ids":{"openalex":"https://openalex.org/W7152033302","doi":"https://doi.org/10.48550/arxiv.2604.06074"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.06074","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06074","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.2604.06074","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133176343","display_name":"Junbin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Junbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133192080","display_name":"Meng Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133155341","display_name":"Feng Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133149369","display_name":"Yikai Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Yikai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133164245","display_name":"Yuexian Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Yuexian","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8410000205039978,"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":0.8410000205039978,"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":0.04780000075697899,"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":0.009399999864399433,"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/scalability","display_name":"Scalability","score":0.5763000249862671},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4925999939441681},{"id":"https://openalex.org/keywords/adjacency-matrix","display_name":"Adjacency matrix","score":0.423799991607666},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4122999906539917},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.40459999442100525},{"id":"https://openalex.org/keywords/laplacian-matrix","display_name":"Laplacian matrix","score":0.3880999982357025},{"id":"https://openalex.org/keywords/adjacency-list","display_name":"Adjacency list","score":0.38029998540878296},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37209999561309814},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.37049999833106995},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.36820000410079956}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7063000202178955},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5763000249862671},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5552999973297119},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C180356752","wikidata":"https://www.wikidata.org/wiki/Q727035","display_name":"Adjacency matrix","level":3,"score":0.423799991607666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4196999967098236},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4122999906539917},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.40459999442100525},{"id":"https://openalex.org/C115178988","wikidata":"https://www.wikidata.org/wiki/Q772067","display_name":"Laplacian matrix","level":3,"score":0.3880999982357025},{"id":"https://openalex.org/C110484373","wikidata":"https://www.wikidata.org/wiki/Q264398","display_name":"Adjacency list","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3774999976158142},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.36820000410079956},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C110893760","wikidata":"https://www.wikidata.org/wiki/Q3115590","display_name":"Named graph","level":5,"score":0.3465999960899353},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3328000009059906},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C165700671","wikidata":"https://www.wikidata.org/wiki/Q203484","display_name":"Laplace operator","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C201943243","wikidata":"https://www.wikidata.org/wiki/Q7551008","display_name":"Social connectedness","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C558772884","wikidata":"https://www.wikidata.org/wiki/Q1508564","display_name":"Graph rewriting","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.2542000114917755},{"id":"https://openalex.org/C2776800370","wikidata":"https://www.wikidata.org/wiki/Q5172864","display_name":"Correlative","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.06074","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06074","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.2604.06074","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.06074","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Achieving":[0],"fine-grained":[1,100],"and":[2,23,29,70,99,121,143,199],"structurally":[3],"sound":[4],"controllability":[5],"is":[6,82,177,209],"a":[7,48,60,83,116,197],"cornerstone":[8],"of":[9,56,79,191],"advanced":[10],"visual":[11,57,66],"generation.":[12],"Existing":[13],"part-based":[14],"frameworks":[15],"treat":[16],"user-provided":[17],"parts":[18,67,128],"as":[19,68,74],"an":[20,122],"unordered":[21],"set":[22],"therefore":[24],"ignore":[25],"their":[26,71],"intrinsic":[27],"spatial":[28],"semantic":[30],"relationships,":[31],"which":[32],"often":[33],"results":[34],"in":[35],"compositions":[36],"that":[37,50,90,126,154,173],"lack":[38],"structural":[39,54,157],"integrity.":[40],"To":[41],"bridge":[42],"this":[43],"gap,":[44],"we":[45,64],"propose":[46],"Graph-PiT,":[47],"framework":[49],"explicitly":[51],"models":[52],"the":[53,77,110,166,189],"dependencies":[55],"components":[58],"using":[59],"graph":[61,117],"prior.":[62],"Specifically,":[63],"represent":[65],"nodes":[69],"spatial-semantic":[72],"relationships":[73],"edges.":[75],"At":[76],"heart":[78],"our":[80],"method":[81],"Hierarchical":[84],"Graph":[85],"Neural":[86],"Network":[87],"(HGNN)":[88],"module":[89],"performs":[91],"bidirectional":[92],"message":[93],"passing":[94],"between":[95],"coarse-grained":[96],"part-level":[97],"super-nodes":[98],"IP+":[101],"token":[102],"sub-nodes,":[103],"refining":[104],"part":[105],"embeddings":[106],"before":[107],"they":[108],"enter":[109],"generative":[111],"pipeline.":[112,169],"We":[113],"also":[114,195],"introduce":[115],"Laplacian":[118],"smoothness":[119],"loss":[120,124],"edge-reconstruction":[123],"so":[125],"adjacent":[127],"acquire":[129],"compatible,":[130],"relation-aware":[131],"embeddings.":[132],"Quantitative":[133],"experiments":[134,171],"on":[135],"controlled":[136],"synthetic":[137],"domains":[138],"(character,":[139],"product,":[140],"indoor":[141],"layout,":[142],"jigsaw),":[144],"together":[145],"with":[146,165],"qualitative":[147],"transfer":[148],"to":[149],"real":[150],"web":[151],"images,":[152],"show":[153],"Graph-PiT":[155],"improves":[156],"coherence":[158],"over":[159],"vanilla":[160],"PiT":[161],"while":[162],"remaining":[163],"compatible":[164],"original":[167],"IP-Prior":[168],"Ablation":[170],"confirm":[172],"explicit":[174],"relational":[175],"reasoning":[176],"crucial":[178],"for":[179,202],"enforcing":[180],"user-specified":[181],"adjacency":[182],"constraints.":[183],"Our":[184],"approach":[185],"not":[186],"only":[187],"enhances":[188],"plausibility":[190],"generated":[192],"concepts":[193],"but":[194],"offers":[196],"scalable":[198],"interpretable":[200],"mechanism":[201],"complex,":[203],"multi-part":[204],"image":[205],"synthesis.":[206],"The":[207],"code":[208],"available":[210],"at":[211],"https://github.com/wolf-bailang/Graph-PiT.":[212]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-09T00:00:00"}