{"id":"https://openalex.org/W7160936770","doi":"https://doi.org/10.48550/arxiv.2605.10588","title":"Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence","display_name":"Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160936770","doi":"https://doi.org/10.48550/arxiv.2605.10588"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2605.10588","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.10588","pdf_url":"https://arxiv.org/pdf/2605.10588","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2605.10588","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133285803","display_name":"Yanbing Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156809","display_name":"Future Academy","ror":"https://ror.org/0570trv98","country_code":"EG","type":"education","lineage":["https://openalex.org/I4210156809"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Zhang, Yanbing","raw_affiliation_strings":["Future Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future Academy","institution_ids":["https://openalex.org/I4210156809"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135919806","display_name":"Bo Wang","orcid":"https://orcid.org/0000-0003-3791-2727","observed_orcids":["https://orcid.org/0000-0003-3791-2727","https://orcid.org/0000-0003-4226-4963","https://orcid.org/0009-0002-6995-6476"]},"institutions":[{"id":"https://openalex.org/I4210156809","display_name":"Future Academy","ror":"https://ror.org/0570trv98","country_code":"EG","type":"education","lineage":["https://openalex.org/I4210156809"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Wang, Bo","raw_affiliation_strings":["Future Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future Academy","institution_ids":["https://openalex.org/I4210156809"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135588059","display_name":"Jianhui Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156809","display_name":"Future Academy","ror":"https://ror.org/0570trv98","country_code":"EG","type":"education","lineage":["https://openalex.org/I4210156809"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Liu, Jianhui","raw_affiliation_strings":["Future Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future Academy","institution_ids":["https://openalex.org/I4210156809"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135981079","display_name":"Nan Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156809","display_name":"Future Academy","ror":"https://ror.org/0570trv98","country_code":"EG","type":"education","lineage":["https://openalex.org/I4210156809"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Jiang, Nan","raw_affiliation_strings":["Future Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future Academy","institution_ids":["https://openalex.org/I4210156809"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133310120","display_name":"Jiaxiu Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156809","display_name":"Future Academy","ror":"https://ror.org/0570trv98","country_code":"EG","type":"education","lineage":["https://openalex.org/I4210156809"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Jiang, Jiaxiu","raw_affiliation_strings":["Future Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future Academy","institution_ids":["https://openalex.org/I4210156809"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132593085","display_name":"Haoze Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156809","display_name":"Future Academy","ror":"https://ror.org/0570trv98","country_code":"EG","type":"education","lineage":["https://openalex.org/I4210156809"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Sun, Haoze","raw_affiliation_strings":["Future Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future Academy","institution_ids":["https://openalex.org/I4210156809"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123526395","display_name":"Yijun Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156809","display_name":"Future Academy","ror":"https://ror.org/0570trv98","country_code":"EG","type":"education","lineage":["https://openalex.org/I4210156809"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Yang, Yijun","raw_affiliation_strings":["Future Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future Academy","institution_ids":["https://openalex.org/I4210156809"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000186521","display_name":"Shenghe Zheng","orcid":"https://orcid.org/0000-0003-0522-2975","observed_orcids":["https://orcid.org/0000-0003-0522-2975"]},"institutions":[{"id":"https://openalex.org/I4210156809","display_name":"Future Academy","ror":"https://ror.org/0570trv98","country_code":"EG","type":"education","lineage":["https://openalex.org/I4210156809"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Zheng, Shenghe","raw_affiliation_strings":["Future Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future Academy","institution_ids":["https://openalex.org/I4210156809"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133115677","display_name":"Lin Song","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156809","display_name":"Future Academy","ror":"https://ror.org/0570trv98","country_code":"EG","type":"education","lineage":["https://openalex.org/I4210156809"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Song, Lin","raw_affiliation_strings":["Future Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future Academy","institution_ids":["https://openalex.org/I4210156809"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020769158","display_name":"Haoyang Huang","orcid":"https://orcid.org/0009-0009-1431-9112","observed_orcids":["https://orcid.org/0009-0009-1431-9112","https://orcid.org/0009-0000-7061-2713","https://orcid.org/0000-0002-3804-5437"]},"institutions":[{"id":"https://openalex.org/I4210156809","display_name":"Future Academy","ror":"https://ror.org/0570trv98","country_code":"EG","type":"education","lineage":["https://openalex.org/I4210156809"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Huang, Haoyang","raw_affiliation_strings":["Future Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future Academy","institution_ids":["https://openalex.org/I4210156809"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138266330","display_name":"Nan Duan","orcid":"https://orcid.org/0000-0002-3387-4674","observed_orcids":["https://orcid.org/0000-0002-3387-4674"]},"institutions":[{"id":"https://openalex.org/I4210156809","display_name":"Future Academy","ror":"https://ror.org/0570trv98","country_code":"EG","type":"education","lineage":["https://openalex.org/I4210156809"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Duan, Nan","raw_affiliation_strings":["Future Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future Academy","institution_ids":["https://openalex.org/I4210156809"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135988357","display_name":"Wenbo Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156809","display_name":"Future Academy","ror":"https://ror.org/0570trv98","country_code":"EG","type":"education","lineage":["https://openalex.org/I4210156809"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Li, Wenbo","raw_affiliation_strings":["Future Academy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Future Academy","institution_ids":["https://openalex.org/I4210156809"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210156809"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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/T10653","display_name":"Robot Manipulation and Learning","score":9.999999747378752e-05,"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/T10036","display_name":"Advanced Neural Network Applications","score":9.999999747378752e-05,"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/spatial-reasoning","display_name":"spatial reasoning","score":0.656000018119812},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"view synthesis","score":0.6499999761581421},{"id":"https://openalex.org/keywords/novel-view-generation","display_name":"novel view generation","score":0.7910000085830688},{"id":"https://openalex.org/keywords/large-multimodal-models","display_name":"large multimodal models","score":0.8939999938011169},{"id":"https://openalex.org/keywords/spatial-ambiguity","display_name":"spatial ambiguity","score":0.48399999737739563},{"id":"https://openalex.org/keywords/spatial-ability","display_name":"spatial ability","score":0.5419999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7089999914169312},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.6771000027656555},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.6104999780654907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5630999803543091},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5519999861717224},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4447000026702881},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C2778662690","wikidata":"https://www.wikidata.org/wiki/Q3125339","display_name":"Spatial ability","level":3,"score":0.37950000166893005},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C107524782","wikidata":"https://www.wikidata.org/wiki/Q40164","display_name":"Lever","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C517642484","wikidata":"https://www.wikidata.org/wiki/Q2388514","display_name":"Intelligence analysis","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C2780342009","wikidata":"https://www.wikidata.org/wiki/Q18387795","display_name":"Perspective-taking","level":3,"score":0.2856000065803528},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2768000066280365},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2646999955177307}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2605.10588","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.10588","pdf_url":"https://arxiv.org/pdf/2605.10588","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.2605.10588","doi":"https://doi.org/10.48550/arxiv.2605.10588","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10588","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:2605.10588","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.10588","pdf_url":"https://arxiv.org/pdf/2605.10588","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/W7160936770.pdf","grobid_xml":"https://content.openalex.org/works/W7160936770.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W4327810158","https://openalex.org/W4403662644","https://openalex.org/W4406975803","https://openalex.org/W4413926275","https://openalex.org/W4414588530","https://openalex.org/W4415795688","https://openalex.org/W4416056960","https://openalex.org/W4416341260","https://openalex.org/W4416378724","https://openalex.org/W4416613140","https://openalex.org/W4416780398","https://openalex.org/W4416935857","https://openalex.org/W4416975798","https://openalex.org/W4417114791","https://openalex.org/W4417308961","https://openalex.org/W6948369276","https://openalex.org/W6966874861","https://openalex.org/W7104817213","https://openalex.org/W7105740705","https://openalex.org/W7119523234","https://openalex.org/W7119597214","https://openalex.org/W7125128317","https://openalex.org/W7155397894"],"related_works":["https://openalex.org/W7223158820","https://openalex.org/W7222155109","https://openalex.org/W7221571222","https://openalex.org/W7220723595","https://openalex.org/W7202213785","https://openalex.org/W4415183921","https://openalex.org/W7161719248","https://openalex.org/W7155041987","https://openalex.org/W4416437584","https://openalex.org/W7163422337"],"abstract_inverted_index":{"Current":[0],"Large":[1],"Multimodal":[2],"Models":[3],"(LMMs)":[4],"struggle":[5],"with":[6,26,59,94,138],"spatial":[7,45,96,118,156],"reasoning":[8,39],"tasks":[9],"requiring":[10],"viewpoint-dependent":[11],"understanding,":[12],"largely":[13],"because":[14],"they":[15],"are":[16],"confined":[17],"to":[18,50,135],"a":[19,30,41,48,151],"single,":[20],"static":[21],"observation.":[22],"We":[23],"propose":[24],"Thinking":[25],"Novel":[27],"Views":[28],"(TwNV),":[29],"paradigm":[31],"that":[32],"integrates":[33],"generative":[34],"novel-view":[35,148],"synthesis":[36],"into":[37],"the":[38,57,60,139],"loop:":[40],"Reasoner":[42],"LMM":[43,123],"identifies":[44],"ambiguity,":[46],"instructs":[47],"Painter":[49],"synthesize":[51],"an":[52],"alternative":[53],"viewpoint,":[54],"and":[55,121,127],"re-examines":[56],"scene":[58],"additional":[61],"evidence.":[62],"Through":[63],"systematic":[64],"experiments":[65],"we":[66],"address":[67],"three":[68],"research":[69],"questions.":[70],"(1)":[71],"Instruction":[72],"format:":[73],"numerical":[74],"camera-pose":[75],"specifications":[76],"yield":[77],"more":[78],"reliable":[79],"view":[80,89,104],"control":[81],"than":[82],"free-form":[83],"language.":[84],"(2)":[85],"Generation":[86],"fidelity:":[87],"synthesized":[88],"quality":[90],"is":[91],"tightly":[92],"coupled":[93],"downstream":[95],"accuracy.":[97],"(3)":[98],"Inference-time":[99],"visual":[100],"scaling:":[101],"iterative":[102],"multi-turn":[103],"refinement":[105],"further":[106],"improves":[107,131],"performance,":[108],"echoing":[109],"recent":[110],"scaling":[111],"trends":[112],"in":[113],"language":[114],"reasoning.":[115],"Across":[116],"four":[117,122],"subtask":[119],"categories":[120],"architectures":[124],"(both":[125],"closed-":[126],"open-source),":[128],"TwNV":[129],"consistently":[130],"accuracy":[132],"by":[133],"+1.3":[134],"+3.9":[136],"pp,":[137],"largest":[140],"gains":[141],"on":[142],"viewpoint-sensitive":[143],"subtasks.":[144],"These":[145],"results":[146],"establish":[147],"generation":[149],"as":[150],"practical":[152],"lever":[153],"for":[154],"advancing":[155],"intelligence":[157],"of":[158],"LMMs.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-05-13T00:00:00"}
