{"id":"https://openalex.org/W7119987610","doi":"https://doi.org/10.48550/arxiv.2601.05138","title":"VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control","display_name":"VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control","publication_year":2026,"publication_date":"2026-01-08","ids":{"openalex":"https://openalex.org/W7119987610","doi":"https://doi.org/10.48550/arxiv.2601.05138"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.05138","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.05138","pdf_url":"https://arxiv.org/pdf/2601.05138","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.05138","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090851249","display_name":"Sixiao Zheng","orcid":"https://orcid.org/0000-0001-8324-1528","observed_orcids":["https://orcid.org/0000-0001-8324-1528"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Sixiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113265293","display_name":"Maolong Yin","orcid":"https://orcid.org/0009-0003-5073-7393","observed_orcids":["https://orcid.org/0009-0003-5073-7393"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Minghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107649418","display_name":"Wenbo Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Wenbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449177","display_name":"Xiaoyu Li","orcid":"https://orcid.org/0000-0003-2588-1687","observed_orcids":["https://orcid.org/0000-0003-2588-1687"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325","observed_orcids":["https://orcid.org/0000-0001-7673-8325"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan, Ying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125707101","display_name":"Yanwei Fu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Yanwei","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":0.9994999766349792,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","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/T10719","display_name":"3D Shape Modeling and Analysis","score":9.999999747378752e-05,"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"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/video-world-models","display_name":"video world models","score":0.8859999775886536},{"id":"https://openalex.org/keywords/3d-gaussian-splatting","display_name":"3D Gaussian Splatting","score":0.8259999752044678},{"id":"https://openalex.org/keywords/video-diffusion-models","display_name":"video diffusion models","score":0.6589999794960022},{"id":"https://openalex.org/keywords/camera-motion-control","display_name":"camera motion control","score":0.671999990940094},{"id":"https://openalex.org/keywords/automatic-training-data-generation","display_name":"automatic training data generation","score":0.5809999704360962}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7172999978065491},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.654699981212616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5979999899864197},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5181000232696533},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4952000081539154},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.26440000534057617},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.05138","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.05138","pdf_url":"https://arxiv.org/pdf/2601.05138","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.05138","doi":"https://doi.org/10.48550/arxiv.2601.05138","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.05138","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.05138","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.05138","pdf_url":"https://arxiv.org/pdf/2601.05138","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":null,"license_id":null,"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":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7111131148","https://openalex.org/W7220745016","https://openalex.org/W4417087253","https://openalex.org/W4417077838","https://openalex.org/W7162293033","https://openalex.org/W7167277759","https://openalex.org/W4415937852","https://openalex.org/W7163178414","https://openalex.org/W7172300842","https://openalex.org/W7220725174"],"abstract_inverted_index":{"Video":[0],"world":[1,45,57,73],"models":[2],"aim":[3],"to":[4,13,104],"simulate":[5],"dynamic,":[6,49],"real-world":[7,152],"environments,":[8],"yet":[9],"existing":[10],"methods":[11],"struggle":[12],"provide":[14],"unified":[15,54],"and":[16,21,81,93,108,148,162,176,182],"precise":[17],"control":[18,118,165,179],"over":[19,97,180],"camera":[20,181],"multi-object":[22,183],"motion,":[23],"as":[24,75],"videos":[25,51],"inherently":[26],"capture":[27],"dynamics":[28],"in":[29],"the":[30,72,134],"projected":[31],"2D":[32],"image":[33],"plane.":[34],"To":[35,137],"bridge":[36],"this":[37],"gap,":[38],"we":[39,142],"introduce":[40],"VerseCrafter,":[41],"a":[42,53,64,76,100,121,151],"geometry-driven":[43],"video":[44,123,129],"model":[46],"that":[47,131,170],"generates":[48],"realistic":[50],"from":[52],"4D":[55,66,113,117,164],"geometric":[56],"state.":[58],"Our":[59],"approach":[60],"is":[61],"centered":[62],"on":[63],"novel":[65],"Geometric":[67,114],"Control":[68,115],"representation,":[69],"which":[70],"encodes":[71],"state":[74],"static":[77],"background":[78],"point":[79],"cloud":[80],"per-object":[82],"3D":[83,95],"Gaussian":[84],"trajectories.":[85],"This":[86],"representation":[87],"captures":[88],"each":[89],"object's":[90],"motion":[91,184],"path":[92],"probabilistic":[94],"occupancy":[96],"time,":[98],"providing":[99],"flexible,":[101],"category-agnostic":[102],"alternative":[103],"rigid":[105],"bounding":[106],"boxes":[107],"parametric":[109],"models.":[110],"We":[111],"render":[112],"into":[116],"maps":[119],"for":[120],"pretrained":[122],"diffusion":[124],"model,":[125],"enabling":[126],"high-fidelity,":[127],"view-consistent":[128],"generation":[130],"faithfully":[132],"follows":[133],"specified":[135],"dynamics.":[136],"enable":[138],"training":[139,156],"at":[140],"scale,":[141],"develop":[143],"an":[144],"automatic":[145],"data":[146],"engine":[147],"construct":[149],"VerseControl4D,":[150],"dataset":[153],"of":[154],"35K":[155],"samples":[157],"with":[158],"automatically":[159],"derived":[160],"prompts":[161],"rendered":[163],"maps.":[166],"Extensive":[167],"experiments":[168],"show":[169],"VerseCrafter":[171],"achieves":[172],"superior":[173],"visual":[174],"quality":[175],"more":[177],"accurate":[178],"than":[185],"prior":[186],"methods.":[187]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-10T00:00:00"}