{"id":"https://openalex.org/W4405562802","doi":"https://doi.org/10.1109/iccv51701.2025.01415","title":"CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models","display_name":"CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4405562802","doi":"https://doi.org/10.1109/iccv51701.2025.01415"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.13195","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084355600","display_name":"Gaoyang Zhang","orcid":"https://orcid.org/0000-0001-7359-256X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaoyang Zhang","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103233480","display_name":"Bao\u2010Quan Fu","orcid":"https://orcid.org/0000-0002-3938-1336"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingtao Fu","raw_affiliation_strings":["Ant Group,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030729327","display_name":"Qingnan Fan","orcid":"https://orcid.org/0000-0003-1249-2826"},"institutions":[{"id":"https://openalex.org/I4210125111","display_name":"Vietnamese Voluntary Foundation","ror":"https://ror.org/032eyp751","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210125111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qingnan Fan","raw_affiliation_strings":["vivo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo,China","institution_ids":["https://openalex.org/I4210125111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360314","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0002-5172-2359"},"institutions":[{"id":"https://openalex.org/I4210125111","display_name":"Vietnamese Voluntary Foundation","ror":"https://ror.org/032eyp751","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210125111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["vivo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo,China","institution_ids":["https://openalex.org/I4210125111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036899956","display_name":"Runxing Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125111","display_name":"Vietnamese Voluntary Foundation","ror":"https://ror.org/032eyp751","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210125111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Runxing Liu","raw_affiliation_strings":["vivo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo,China","institution_ids":["https://openalex.org/I4210125111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101434406","display_name":"Hong Gu","orcid":"https://orcid.org/0000-0002-8224-146X"},"institutions":[{"id":"https://openalex.org/I4210125111","display_name":"Vietnamese Voluntary Foundation","ror":"https://ror.org/032eyp751","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210125111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Gu","raw_affiliation_strings":["vivo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo,China","institution_ids":["https://openalex.org/I4210125111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015850101","display_name":"Huaqi Zhang","orcid":"https://orcid.org/0000-0001-5891-6204"},"institutions":[{"id":"https://openalex.org/I4210125111","display_name":"Vietnamese Voluntary Foundation","ror":"https://ror.org/032eyp751","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210125111"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaqi Zhang","raw_affiliation_strings":["vivo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"vivo,China","institution_ids":["https://openalex.org/I4210125111"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075268342","display_name":"Xinguo Liu","orcid":"https://orcid.org/0000-0003-4650-1970"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinguo Liu","raw_affiliation_strings":["Zhejiang University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.00141088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15253","last_page":"15265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9517999887466431,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9517999887466431,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.951200008392334,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/compass","display_name":"Compass","score":0.8443650007247925},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.53725665807724},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46304231882095337},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46056845784187317},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44717124104499817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40887707471847534},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.3693392872810364},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.32169198989868164},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16762635111808777}],"concepts":[{"id":"https://openalex.org/C2778361833","wikidata":"https://www.wikidata.org/wiki/Q34735","display_name":"Compass","level":2,"score":0.8443650007247925},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.53725665807724},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46304231882095337},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46056845784187317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44717124104499817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40887707471847534},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.3693392872810364},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.32169198989868164},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16762635111808777},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.13195","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.13195","pdf_url":"https://arxiv.org/pdf/2412.13195","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.13195","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.13195","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":"pmh:oai:arXiv.org:2412.13195","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.13195","pdf_url":"https://arxiv.org/pdf/2412.13195","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8788252494","display_name":null,"funder_award_id":"62032011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206872286","https://openalex.org/W2382913035","https://openalex.org/W2113447385","https://openalex.org/W2391335452","https://openalex.org/W2360876323","https://openalex.org/W2109954054","https://openalex.org/W2642723128","https://openalex.org/W1970764900","https://openalex.org/W2366280361","https://openalex.org/W638953695"],"abstract_inverted_index":{"Text-to-image":[0],"(T2I)":[1],"diffusion":[2],"models":[3,124],"excel":[4],"at":[5,158],"generating":[6],"photorealistic":[7],"images":[8],"but":[9],"often":[10],"fail":[11],"to":[12,46],"render":[13],"accurate":[14],"spatial":[15,33,50,63,139],"relationships.":[16],"We":[17,55],"identify":[18],"two":[19],"core":[20],"issues":[21],"underlying":[22],"this":[23],"common":[24],"failure:":[25],"1)":[26],"the":[27,40,49,74,96,114,135],"ambiguous":[28],"nature":[29],"of":[30,42,52,134],"data":[31,71,79,85],"concerning":[32],"relationships":[34],"in":[35,65],"existing":[36],"datasets,":[37],"and":[38,126,151],"2)":[39],"inability":[41],"current":[43],"text":[44,110],"encoders":[45],"accurately":[47],"interpret":[48],"semantics":[51],"input":[53],"descriptions.":[54],"propose":[56],"CoMPaSS,":[57],"a":[58,131],"versatile":[59],"framework":[60],"that":[61],"enhances":[62],"understanding":[64],"T2I":[66,123],"models.":[67],"It":[68],"first":[69],"addresses":[70],"ambiguity":[72],"with":[73,141],"Spatial":[75,149],"Constraints-Oriented":[76],"Pairing":[77],"(SCOP)":[78],"engine,":[80],"which":[81,102],"curates":[82],"spatially-accurate":[83],"training":[84],"via":[86],"principled":[87],"constraints.":[88],"To":[89],"leverage":[90],"these":[91],"priors,":[92],"CoMPaSS":[93,129],"also":[94],"introduces":[95],"Token":[97],"ENcoding":[98],"ORdering":[99],"(TENOR)":[100],"module,":[101],"preserves":[103],"crucial":[104],"token":[105],"ordering":[106],"information":[107],"lost":[108],"by":[109],"encoders,":[111],"thereby":[112],"reinforcing":[113],"prompt's":[115],"linguistic":[116],"structure.":[117],"Extensive":[118],"experiments":[119],"on":[120,137,145],"four":[121],"popular":[122],"(UNet":[125],"MMDiT-based)":[127],"show":[128],"sets":[130],"new":[132],"state":[133],"art":[136],"key":[138],"benchmarks,":[140],"substantial":[142],"relative":[143],"gains":[144],"VISOR":[146],"(+98%),":[147],"T2I-CompBench":[148],"(+67%),":[150],"GenEval":[152],"Position":[153],"(+131%).":[154],"Code":[155],"is":[156],"available":[157],"https://github.com/blurgyy/CoMPaSS.":[159]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}
