{"id":"https://openalex.org/W4415182079","doi":"https://doi.org/10.1109/iccv51701.2025.01475","title":"Rethink Sparse Signals for Pose-Guided Text-to-Image Generation","display_name":"Rethink Sparse Signals for Pose-Guided Text-to-Image Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415182079","doi":"https://doi.org/10.1109/iccv51701.2025.01475"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01475","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.20983","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103145956","display_name":"Wenjie Xuan","orcid":"https://orcid.org/0000-0003-1579-2218"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Xuan","raw_affiliation_strings":["School of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032383728","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0003-1290-0738"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026501335","display_name":"Juhua Liu","orcid":"https://orcid.org/0000-0002-3907-8820"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juhua Liu","raw_affiliation_strings":["School of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060042752","display_name":"Bo Du","orcid":"https://orcid.org/0000-0002-0059-8458"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Du","raw_affiliation_strings":["School of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101409300","display_name":"Dacheng Tao","orcid":"https://orcid.org/0000-0002-5979-578X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"15896","last_page":"15906"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9787999987602234,"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":0.9764000177383423,"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/discriminative-model","display_name":"Discriminative model","score":0.7369999885559082},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.6082000136375427},{"id":"https://openalex.org/keywords/simplicity","display_name":"Simplicity","score":0.508400022983551},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48089998960494995},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.3984000086784363},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.37470000982284546},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.337799996137619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7425000071525574},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7369999885559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6351000070571899},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.6082000136375427},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3529999852180481},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.2939999997615814},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C77637269","wikidata":"https://www.wikidata.org/wiki/Q7002051","display_name":"Neural coding","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25440001487731934},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01475","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:2506.20983","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.20983","pdf_url":"https://arxiv.org/pdf/2506.20983","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.20983","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.20983","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.20983","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.20983","pdf_url":"https://arxiv.org/pdf/2506.20983","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3500813470","display_name":null,"funder_award_id":"RF-P2024-001","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"},{"id":"https://openalex.org/G4017765273","display_name":null,"funder_award_id":"U23B2048,623B2076,62225113","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8400922664","display_name":null,"funder_award_id":"2023YFC2705700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"works":[1],"favored":[2],"dense":[3,26,144],"signals":[4,13,47,70],"(e.g.,":[5,14],"depth,":[6],"DensePose),":[7],"as":[8],"an":[9],"alternative":[10],"to":[11,16,44,52,82,103,105],"sparse":[12,46,69,158],"OpenPose),":[15],"provide":[17],"detailed":[18],"spatial":[19,85,107],"guidance":[20,137],"for":[21,48,74],"pose-guided":[22,75],"text-to-image":[23],"generation.":[24,77],"However,":[25],"representations":[27],"raised":[28],"new":[29],"challenges,":[30],"including":[31],"editing":[32],"difficulties":[33],"and":[34,55,91,119,138,154],"potential":[35],"inconsistencies":[36],"with":[37,71],"textual":[38],"prompts.":[39],"This":[40,61],"fact":[41],"motivates":[42],"us":[43],"revisit":[45],"pose":[49,114],"guidance,":[50],"owing":[51],"their":[53],"simplicity":[54],"shape-agnostic":[56],"nature,":[57],"which":[58,99],"remains":[59],"underexplored.":[60],"paper":[62],"proposes":[63],"a":[64,83],"novel":[65],"Spatial-Pose":[66],"ControlNet(SP-Ctrl),":[67],"equipping":[68],"robust":[72],"controllability":[73],"image":[76,121],"Specifically,":[78],"we":[79,94],"extend":[80],"OpenPose":[81],"learnable":[84],"representation,":[86],"making":[87],"keypoint":[88,96,101],"embeddings":[89],"discriminative":[90],"expressive.":[92],"Additionally,":[93],"introduce":[95],"concept":[97],"learning,":[98],"encourages":[100],"tokens":[102],"attend":[104],"the":[106,141],"positions":[108],"of":[109,143],"each":[110],"keypoint,":[111],"thus":[112],"improving":[113],"alignment.":[115],"Experiments":[116],"on":[117],"animal-":[118],"human-centric":[120],"generation":[122,133,156],"tasks":[123],"demonstrate":[124],"that":[125],"our":[126],"method":[127],"outperforms":[128],"recent":[129],"spatially":[130],"controllable":[131],"T2I":[132],"approaches":[134],"under":[135],"sparse-pose":[136],"even":[139],"matches":[140],"performance":[142],"signal-based":[145],"methods.":[146],"Moreover,":[147],"SP-Ctrl":[148],"shows":[149],"promising":[150],"capabilities":[151],"in":[152],"diverse":[153],"cross-species":[155],"through":[157],"signals.":[159],"Codes":[160],"will":[161],"be":[162],"available":[163],"at":[164],"https://github.com/DREAMXFAR/SP-Ctrl.":[165]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-15T00:00:00"}