{"id":"https://openalex.org/W7168599943","doi":"https://doi.org/10.1145/3799902.3811152","title":"Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation","display_name":"Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7168599943","doi":"https://doi.org/10.1145/3799902.3811152"},"language":null,"primary_location":{"id":"doi:10.1145/3799902.3811152","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811152","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3799902.3811152","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074331986","display_name":"Siyou Lin","orcid":"https://orcid.org/0000-0002-8906-657X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyou Lin","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8906-657X","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741728","display_name":"Zhou Xue","orcid":"https://orcid.org/0000-0002-3157-6606"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Xue","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3157-6606","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100670025","display_name":"Hongwen Zhang","orcid":"https://orcid.org/0000-0001-8633-4551"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwen Zhang","raw_affiliation_strings":["Beijing Normal University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8633-4551","affiliations":[{"raw_affiliation_string":"Beijing Normal University, Beijing, China","institution_ids":["https://openalex.org/I25254941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102019986","display_name":"Liang An","orcid":"https://orcid.org/0000-0002-1028-3759"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang An","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1028-3759","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100779878","display_name":"Dongping Li","orcid":"https://orcid.org/0009-0003-9967-1145"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongping Li","raw_affiliation_strings":["ByteDance Inc., Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-9967-1145","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002247613","display_name":"Shaohui Jiao","orcid":"https://orcid.org/0009-0002-5350-6809"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaohui Jiao","raw_affiliation_strings":["ByteDance Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-5350-6809","affiliations":[{"raw_affiliation_string":"ByteDance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032875389","display_name":"Yebin Liu","orcid":"https://orcid.org/0000-0003-3215-0225"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yebin Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3215-0225","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6481999754905701},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6259999871253967},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.5691999793052673},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.5297999978065491},{"id":"https://openalex.org/keywords/mixing","display_name":"Mixing (physics)","score":0.5085999965667725},{"id":"https://openalex.org/keywords/articulated-body-pose-estimation","display_name":"Articulated body pose estimation","score":0.4519999921321869},{"id":"https://openalex.org/keywords/iterative-reconstruction","display_name":"Iterative reconstruction","score":0.40070000290870667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3804999887943268}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7174999713897705},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6790000200271606},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6481999754905701},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6259999871253967},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.5691999793052673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5569999814033508},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.5297999978065491},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.5085999965667725},{"id":"https://openalex.org/C22100474","wikidata":"https://www.wikidata.org/wiki/Q4800952","display_name":"Articulated body pose estimation","level":4,"score":0.4519999921321869},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3804999887943268},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.3799000084400177},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3264999985694885},{"id":"https://openalex.org/C20885615","wikidata":"https://www.wikidata.org/wiki/Q825595","display_name":"Surface reconstruction","level":3,"score":0.3034999966621399},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28850001096725464},{"id":"https://openalex.org/C70958404","wikidata":"https://www.wikidata.org/wiki/Q7512728","display_name":"Signal reconstruction","level":4,"score":0.27070000767707825},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C2776863239","wikidata":"https://www.wikidata.org/wiki/Q7936601","display_name":"Visual hull","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3799902.3811152","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811152","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3799902.3811152","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3799902.3811152","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1991544872","https://openalex.org/W2471962767","https://openalex.org/W2519683295","https://openalex.org/W2962785568","https://openalex.org/W2981978060","https://openalex.org/W3035291735","https://openalex.org/W3109585842","https://openalex.org/W3177150154","https://openalex.org/W3180196270","https://openalex.org/W4226160668","https://openalex.org/W4285102264","https://openalex.org/W4312453532","https://openalex.org/W4312567873","https://openalex.org/W4312641613","https://openalex.org/W4312933868","https://openalex.org/W4385275714","https://openalex.org/W4385318467","https://openalex.org/W4386065784","https://openalex.org/W4386066388","https://openalex.org/W4386076247","https://openalex.org/W4386076275","https://openalex.org/W4389242781","https://openalex.org/W4390872990","https://openalex.org/W4390889720","https://openalex.org/W4399563654","https://openalex.org/W4400822286","https://openalex.org/W4402753973","https://openalex.org/W4402816534","https://openalex.org/W4403842650","https://openalex.org/W4403888374","https://openalex.org/W4404199644","https://openalex.org/W4405002951","https://openalex.org/W4412673735","https://openalex.org/W4413146238","https://openalex.org/W4413146712","https://openalex.org/W4413146846","https://openalex.org/W4413146851","https://openalex.org/W4413155739","https://openalex.org/W4415795573","https://openalex.org/W4417000825","https://openalex.org/W7133223716","https://openalex.org/W7160143585","https://openalex.org/W7162498741"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"trends":[1],"in":[2,61,70,190],"sparse-view":[3],"3D":[4,27,47,55,68,95,108,130,158,204,217,222,241,250],"reconstruction":[5,12,28,48,53,126,202,263],"have":[6],"taken":[7],"two":[8,71],"different":[9],"paths:":[10],"feed-forward":[11,52,125,201,207,233,262],"(such":[13,29],"as":[14,30],"VGGT)":[15],"that":[16,32,107,119,169],"predicts":[17],"pixel-aligned":[18],"point":[19,100,161],"maps":[20,101],"without":[21],"a":[22,44,58,67,73,79,93,116,124,129,191,215,236],"complete":[23,34],"geometry,":[24],"and":[25,54,78,102,128,160,203,219],"generative":[26,46,86,131,216,251],"TRELLIS)":[31],"generates":[33,66],"geometry":[35,81,177],"but":[36,145],"often":[37],"with":[38,243,248,254],"poor":[39],"input-alignment.":[40],"We":[41],"present":[42],"Mix3R,":[43],"novel":[45],"method":[49,239],"which":[50],"mixes":[51],"generation":[56,76,82,90,178,223],"into":[57],"single":[59],"framework":[60],"an":[62,165],"aligned":[63,105,154],"manner.":[64,193],"Mix3R":[65],"shape":[69],"stages:":[72],"sparse":[74,157],"voxel":[75],"stage":[77],"textured":[80,176],"stage.":[83],"Unlike":[84],"pure":[85,249],"methods,":[87,252],"our":[88,238],"first-stage":[89],"jointly":[91],"produces":[92,240],"coarse":[94],"structure":[96],"(sparse":[97],"voxels),":[98],"per-view":[99],"camera":[103,255],"parameters":[104],"to":[106,123,173,182,199,210,214],"structure.":[109],"This":[110,138],"is":[111,170,225,268],"made":[112],"possible":[113],"by":[114],"introducing":[115],"Mixture-of-Transformers":[117],"architecture":[118],"inserts":[120],"global":[121],"self-attentions":[122],"model":[127],"model,":[132,179],"both":[133,200],"pretrained":[134,143,175],"on":[135,151,227],"large-scale":[136],"data.":[137],"design":[139,195],"effectively":[140],"retains":[141],"the":[142,152,221,232],"priors":[144],"enables":[146],"better":[147,244],"2D-3D":[148],"alignment.":[149],"Based":[150],"initial":[153],"generations":[155],"of":[156],"voxels":[159],"maps,":[162],"we":[163],"compute":[164],"overlap-based":[166],"attention":[167],"bias":[168],"directly":[171],"added":[172],"another":[174],"enabling":[180],"it":[181],"correctly":[183],"place":[184],"input":[185,245],"textures":[186],"onto":[187],"generated":[188],"shapes":[189,242],"training-free":[192],"Our":[194,265],"brings":[196],"mutual":[197],"benefits":[198],"generation:":[205],"The":[206],"branch":[208,224],"learns":[209],"ground":[211],"its":[212],"predictions":[213],"prior,":[218],"conversely,":[220],"conditioned":[226],"geometrically":[228],"informative":[229],"features":[230],"from":[231],"branch.":[234],"As":[235],"result,":[237],"alignment":[246],"compared":[247],"together":[253],"pose":[256],"estimations":[257],"more":[258],"accurate":[259],"than":[260],"previous":[261],"methods.":[264],"project":[266],"page":[267],"at":[269],"https://jsnln.github.io/mix3r/":[270]},"counts_by_year":[],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2026-07-17T00:00:00"}