[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86484-en":3,"doc-seo-86484-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},86484,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Neural Motion Blending Across Arbitrary Character Topologies","Motion blending in character animation synthesizes new motions by interpolating between existing examples. Prior approaches typically assume fixed skeleton topologies, making cross-character blending difficult when joint hierarchies, bone counts, or structural graphs differ. A unified framework is proposed to blend across heterogeneous skeletons by encoding motion semantics into a shared latent space and decoding character-specific motions with a diffusion-based conditional model. Latent interpolation yields smooth, plausible transitions evaluated on Truebones Zoo for both same and distinct topologies.","arXiv :2607 . 10370v1 [ cs .CV] 11 Jul 2026  \nNeural Motion Blending Across Arbitrary Character Topologies  \nLuca Cazzola 1[0009−0000−6285−8342]⋆, Giulia Martinelli 1 ,2[0000−0003−3713−3053]⋆ , and Nicola Conci 1 ,2[0000−0002−7858−0928]  \n1 University of Trento, Trento 38123, Italy  \nluca .cazzola-1@studenti .unitn .it,  \n{giulia.martinelli-2,nicola.conci}@unitn.it  \n2 CNIT, Trento 38123, Italy  \n[https://mmlab-cv.github.io/neural_motion_blending/](https://mmlab-cv.github.io/neural_motion_blending/)  \nAbstract. Motion blending in character animation enables the synthesis of new motions by interpolating between existing examples. Current methods are typically restricted to fixed skeleton topologies, requiring identical or near-identical skeletal structures across characters.  \nWe present a novel framework for motion blending across heterogeneous skeletons. The proposed architecture combines a semantic encoder, which extracts per-frame latent representations of the motion state, with a diffusion-based decoder, which reconstructs character-specific motion conditioned on this latent code. At inference, blended motions are obtained by interpolating the latent representations of two input motions. We train and evaluate the method on the Truebones Zoo dataset using motions defined on both same and distinct skeleton topologies, demonstrating the ability to achieve smooth and plausible blending in a variety of scenarios.  \nKeywords: Motion Blending · Diffusion Autoencoders · Any-Topology.  \n1 Introduction  \nAnimation pipelines involve diverse casts of characters, from humanoids to creatures and stylized avatars, whose skeletal structures vary in topology, proportions, and bone hierarchy. Standard motion blending workflows are generally tied to a fixed skeleton representation, making cross-character interpolation hard to achieve. As a result, animators are often forced to rely on manual correspondence design, retargeting, and cleanup before they can test even simple blended motions [10] . Recent neural approaches have also begun to revisit motion blending as a learnable problem [11,21], aiming to provide more automatic and controllable tools for animators. Still, these approaches do not target cross-topology motion interpolation.  \nYet, some progress has been made also in cross-topology motion synthesis [8,22] and retargeting [1,5 , 14], in part enabled by datasets offering heterogeneous skeletal structures [20] . However, in synthesis, motion is generated from  \n⋆ Denotes equal contribution.  \n2 Cazzola et al.  \nSlow Walking  \nMotion Blending  \nSlow Walking-to-Jump  \nWalk  \nDown  \nSlow  \nCharge  \nJump  \nLand  \n\n|  |  |  |  |  | Time |\n| --- | --- | --- | --- | --- | --- |\n\nFig. 1: We introduce a unified framework for cross-topology motion blending. Given reference motion and a target motion, our method generates a transition while preserving reference skeleton structure. Here, a slow-walking raptor is blended with a jumping lynx using the raptor as reference skeleton, producing a new raptor animation that walks, slows down, charges, jumps, and lands.  \nscratch, and with retargeting motion is transferred form one character to a second one; thus, neither of them directly addresses the problem of blending two existing motions, especially between different topologies as shown in Figure 1.  \nIn this work, we introduce a skeleton-agnostic diffusion autoencoding framework for motion blending across heterogeneous characters. Our key idea is to decouple motion semantics from skeleton-specific realization by factorizing each input motion into a semantic code that captures the global motion state, and a stochastic code that captures fine-grained skeleton-specific variation conditioned on it. A graph-based semantic encoder maps motions from arbitrary topologies into a shared latent space, while a diffusion-based decoder reconstructs skeletonspecific motion conditioned on the semantic representation. Blending is then achieved by interpolating seman","cbCaihJudv3cRVAg","https://ap.wps.com/l/cbCaihJudv3cRVAg","pdf",5055675,6,1,16,"English","en",105,"# Introduction\n## Contributions\n# Related Work\n## Motion Blending","[{\"question\":\"What problem does the paper address in character motion blending?\",\"answer\":\"It addresses motion blending across characters with different skeleton topologies, where conventional methods require identical or near-identical skeletal structures.\"},{\"question\":\"How does the proposed method enable cross-topology blending?\",\"answer\":\"It factorizes motion into a shared semantic latent code and skeleton-specific stochastic components, then reconstructs target character motion using a diffusion-based decoder conditioned on the semantic representation.\"},{\"question\":\"How are blended motions generated at inference time?\",\"answer\":\"Blended motions are produced by interpolating the semantic latent representations of two input motions, and composing the stochastic components to obtain a smooth transition.\"}]",1784212063,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"neural-motion-blending-across-arbitrary-character-topologies","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/neural-motion-blending-across-arbitrary-character-topologies/86484/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-27","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the paper address in character motion blending?","Question",{"text":76,"@type":77},"It addresses motion blending across characters with different skeleton topologies, where conventional methods require identical or near-identical skeletal structures.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the proposed method enable cross-topology blending?",{"text":81,"@type":77},"It factorizes motion into a shared semantic latent code and skeleton-specific stochastic components, then reconstructs target character motion using a diffusion-based decoder conditioned on the semantic representation.",{"name":83,"@type":74,"acceptedAnswer":84},"How are blended motions generated at inference time?",{"text":85,"@type":77},"Blended motions are produced by interpolating the semantic latent representations of two input motions, and composing the stochastic components to obtain a smooth transition.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":107,"slug":137},19,"General","general"]