[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-189121-105":3,"detail-sidebar-cat-1-en-105":73,"doc-detail-189121-en":119},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":66,"head_meta":68,"extra_data":70,"updated_unix":72},105,"en","worldflow3d-results-comparison","WorldFlow3D - Results comparison","","WorldFlow3D is evaluated against several related 3D generation methods using multiple metrics across different datasets and conditioning settings. The document reports quantitative comparisons including COV, MMD (CD/EMD), 1-NNA (CD/EMD), JSD, and FDC, alongside rank and BT score with confidence intervals and win rates. Additional ablation studies vary core modeling components, showing how design choices affect coverage, diversity, and fidelity indicators. Overall results highlight WorldFlow3D’s strong performance relative to baselines.",{"@graph":14,"@context":65},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/template/","Template",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/template/general/","General",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/template/worldflow3d-results-comparison/189121/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/worldflow3d-results-comparison/189121.png","ImageObject",442,249,{"name":42,"@type":43},"Ivy","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-09-29","2026-09-03",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59],{"name":60,"@type":61,"acceptedAnswer":62},"How do ablation variants of WorldFlow3D change the results?","Question",{"text":63,"@type":64},"Ablations test alternatives such as latent diffusion/flow and a “flow from noise” baseline, plus modified WorldFlow3D settings; the table shows corresponding shifts in coverage, diversity, and fidelity metrics.","Answer","https://schema.org",{"og:url":32,"og:type":67,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":69,"canonical":32},"index,follow",{"doc_id":71,"site_id":7},189121,1788394445,{"code":4,"msg":74,"data":75},"success",[76,81,86,91,96,101,106,111,116],{"id":77,"doc_module":22,"doc_module_name":25,"category_name":78,"show_sort_weight":79,"slug":80},11,"Presentations",90,"presentations",{"id":82,"doc_module":22,"doc_module_name":25,"category_name":83,"show_sort_weight":84,"slug":85},12,"Resumes",80,"resumes",{"id":87,"doc_module":22,"doc_module_name":25,"category_name":88,"show_sort_weight":89,"slug":90},14,"Invoices",70,"invoices",{"id":92,"doc_module":22,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},15,"Posters",60,"posters",{"id":97,"doc_module":22,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},16,"Social Media",50,"social-media",{"id":102,"doc_module":22,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},17,"Forms",40,"forms",{"id":107,"doc_module":22,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},18,"Letters",30,"letters",{"id":112,"doc_module":22,"doc_module_name":25,"category_name":113,"show_sort_weight":114,"slug":115},21,"Paper Templates",5,"papers-templates",{"id":117,"doc_module":22,"doc_module_name":25,"category_name":29,"show_sort_weight":4,"slug":118},158,"general-158",{"code":4,"msg":74,"data":120},{"doc_id":71,"user_id":121,"nickname":42,"user_avatar":122,"doc_module":22,"category_id":117,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":123,"file_id":124,"file_url":125,"file_type":126,"file_size":127,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":128,"language":129,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":130,"faqs":131,"seo_title":132,"seo_description":12,"update_tm":72,"read_time":55},549758252649,"https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819","| XCube [31] BlockFusion [42] LidarDM [46] LT3SD [24]\u003Cbr>InfiniCube [23] WorldGrow [18] XScene [44]\u003Cbr>Ours |  |  |  |  |  |  |  |  |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- |\n| Unbounded | \u003Cbr>✁ | \u003Cbr>✂ | \u003Cbr>✁ | \u003Cbr>✂ | \u003Cbr>✂ | \u003Cbr>✂ | \u003Cbr>✂ | \u003Cbr>✂ |\n| Controllable | ✁ | ✁ | ✁ | ✁ | ✂ | ✁ | ✁ | ✂ |\n| Cross-Domain | ✂ | ✂ | ✁ | ✁ | ✁ | ✁ | ✁ | ✂ |\n| Texture | ✁ | ✁ | ✁ | ✁ | ✂ | ✂ | ✂ | ✂ |\n\n|  | Method |  | COV ↑ |  | MMD ↓ |  | 1-NNA ↓ |  |  | JSD ↓ | FDC ↓ |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n|  |  |  | CD | EMD | CD | EMD | CD | EMD |  |  |  |\n| Waymo\u003Cbr>Uncond. | XCube [31] LidarDM [46] LT3SD [24]\u003Cbr>WorldFlow3D |  | 27.50 | 24.90 | 19.75 | 2.99 | 95.85 | 85.35 |  | 0.480 | 214.08 |\n|  |  |  | 15.30 | 15.40 | 29.74 | 3.60 | 99.40 | 98.10 |  | 0.564 | 232.49 |\n|  |  |  | 20.00 | 16.10 | 34.33 | 3.96 | 95.85 | 85.35 |  | 0.524 | 76.04 |\n|  |  |  | 33.00 | 32.70 | 16.57 | 2.81 | 89.15 | 70.15 |  | 0.490 | 74.83 |\n| Waymo\u003Cbr>Cond. | LidarDM [46]\u003Cbr>WorldFlow3D |  | 12.00\u003Cbr>39.70 | 11.30\u003Cbr>35.20 | 35.46\u003Cbr>12.44 | 3.81\u003Cbr>2.70 | 99.60\u003Cbr>88.60 | 99.20\u003Cbr>81.85 |  | 0.590\u003Cbr>0.483 | 215.49 |\n|  |  |  |  |  |  |  |  |  |  |  | 80.08 |\n\n\n|  | Method | COV ↑ |  | MMD ↓ |  | 1-NNA ↓ |  |  | JSD ↓ | FDC ↓ |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n|  |  | CD | EMD | CD | EMD | CD | EMD |  |  |  |\n| 3D-Front\u003Cbr>[12] Uncond. | BlockFusion [42] | 29.00 | 28.40 | 0.054 | 0.221 | 91.50 | 90.65 |  | 0.380 | 165.46 |\n|  | LT3SD [24] | 23.40 | 26.20 | 0.056 | 0.223 | 93.00 | 91.60 |  | 0.230 | 44.97 |\n|  | WorldGrow [18] | 34.70 | 32.80 | 0.053 | 0.221 | 88.05 | 88.65 |  | 0.272 | 172.58 |\n|  | WorldFlow3D | 38.30 | 38.10 | 0.039 | 0.195 | 74.75 | 75.80 |  | 0.164 | 36.45 |\n\n\n| Ablation |  | COV ↑ |  | MMD ↓ |  | 1-NNA ↓ |  |  | FDC ↓ | GPU-hrs ↓ |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n|  |  | CD | EMD | CD | EMD | CD | EMD |  |  |  |\n| Latent Diffusion | 3 | 7.75 | 33.75 | 7.426 | 1.801 | 91.38 | 75.63 |  | 120.87 | 288 |\n| Latent Flow | 3 | 7.00 | 32.75 | 6.755 | 1.778 | 90.88 | 74.88 |  | 112.35 | 288 |\n| Flow from Noise | 3 | 3.75 | 33.75 | 6.887 | 1.747 | 92.25 | 81.25 |  | 107.59 | 144 |\n| WorldFlow3D (p(f) = p (1) ) | 3 |  8.00 | 31.50 | 7.101 | 1.821 | 92.75 | 75.63 |  | 89.47 | 72 |\n| WorldFlow3D(full) | 4 | 2.50 | 37.25 | 4.942 | 1.696 | 85.00 | 70.25 |  | 103.20 | 144 |\n\n| Method | Rank | BT Score | 95% CI | Win Rate |\n| --- | --- | --- | --- | --- |\n| WorldFlow3D | 1 | 0.692 | [0.569, 0.813] | 88% |\n| XCube [31] | 2 | 0.212 | [0.118, 0.314] | 63% |\n| LT3SD [24] | 3 | 0.085 | [0.047, 0.131] | 43% |\n| LidarDM [46] | 4 | 0.011 | [0.004, 0.022] | 6% |","cbCaivdW5PkJcBDh","https://ap.wps.com/l/cbCaivdW5PkJcBDh","pdf",28800886,23,"English","# Evaluation Results\n## Comparative Metrics\n## Ablation Studies\n## Ranking and Win Rate","[{\"question\":\"How do ablation variants of WorldFlow3D change the results?\",\"answer\":\"Ablations test alternatives such as latent diffusion/flow and a “flow from noise” baseline, plus modified WorldFlow3D settings; the table shows corresponding shifts in coverage, diversity, and fidelity metrics.\"}]","WorldFlow3D - Results comparison | PDF"]