[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85974-en":3,"doc-seo-85974-105":29,"detail-sidebar-cat-0-en-105":91},{"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85974,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","PoseAlign: Sculpting Pose-Consistent Meshes via Text-Guided Deformation","Mesh deformation alters vertex positions of a 3D mesh while preserving its topology and is a core task in computer graphics. Despite many emerging text-guided mesh deformation approaches, transferring an initial mesh to one that both matches text prompts and retains the original pose remains difficult. PoseAlign addresses this by splitting deformation into global pose scaling and local detail sculpting, combining Laplacian-based smooth global updates with a pose-aligned SDS loss using attention sharing.","Noname manuscript No.  \n(will be inserted by the editor)  \nPoseAlign: Sculpting Pose-Consistent Meshes via Text-Guided Deformation  \nShijin Wang 1 · Zichong Chen 1 · Yang Zhou 1 · Hui Huang 1  \narXiv :2607 . 10560v1 [ cs .GR] 12 Jul 2026  \nthe date of receipt and acceptance should be inserted later  \nAbstract Mesh deformation, the process of altering the vertex positions of a 3D mesh while preserving its topological structure, is a cornerstone of computer graphics. Despite the recent emergence of numerous textguided 3D mesh deformation methods, deforming an initial mesh into one that both adheres to text promptsand preserves its pose remains challenging. This paper proposes PoseAlign, which decomposes text-guided mesh deformation into two stages: global pose scaling and local detail sculpting. Specifically, in the first stage, we introduce the Laplacian as a differentiable mesh representation to enable more efficient yet smoother global deformation. Then, we propose a novel pose-aligned SDS loss by adapting score distillation sampling (SDS) with an attention-sharing mechanism, which sculptures fine-grained geometric details for the deformed mesh while preserving its original pose. PoseAlign significantly enhances the controllability of the overall deformation process, achieving a favorable balance between pose preservation and text alignment. Experiments demonstrate the competitive advantages of our method in text alignment and mesh quality. Code is available at: [https://cousingrade6.github.io/PoseAlign/](https://cousingrade6.github.io/PoseAlign/) .  \nKeywords Mesh deformation · Geometry representation · Pose-aligned SDS Loss · Attention Mechanism  \n1 Introduction  \nMesh deformation is a fundamental task in computer graphics with broad applications in content creation,  \n􀀌 Yang Zhou [zhouyangvcc@gmail.com](zhouyangvcc@gmail.com)  \n1 Guangdong Provincial Key Lab. of Visual Media and Multidim. Intelligence, CSSE, Shenzhen University, China.  \nFig. 1: Pose-preserved text-guided mesh deformation. Given a source mesh, PoseAlign is capable of deforming it to a target mesh that aligns with the text semantics while preserving its original pose.  \ncharacter posing, morphing, and animation [11,14,18, 42] . Traditional methods rely on geometric priors (e.g, As-Rigid-As-Possible [54], Laplacian deformation [56]), or handle-based controls [24,55], which require significant manual efforts to achieve plausible results.  \nThe advent of Vision-Language Models (VLMs) [38, 47,33] and diffusion models [48,45,51] has revolutionized this domain by enabling text-guided deformation, where natural language prompts intuitively drive geometric manipulation. Moreover, per-face Jacobian [1] emerged as a pivotal differential representation, replacing direct vertex displacements to prioritize smoother deformations. Text-driven methods leverage differentiable rendering and pretrained models (e.g., the CLIP [47] or diffusion models [48]) to connect geometry with tex-  \nFig. 2: Motivation of PoseAlign. Given the source mesh displayed in Fig. 1, we aim to deform it to conform to user-specified textual descriptions. Previous techniques, such as TextDeformer and MeshUp, exhibit severe limitations in generating high-fidelity meshes that simultaneously preserve the source mesh’s pose and achieve semantic alignment with the input text. Our approach builds upon these observations and yields meshes with significantly improved quality, more precise pose preservation, and enhanced text fidelity.  \ntual semantics, transforming deformation into an optimization problem guided by text-image alignment.  \nHowever, current methods [19,69,29] often fall short in two aspects: large-scale deformation quality and pose preservation. As shown in Fig. 2, TextDeformer [19] partially preserves the pose of the input source mesh but struggles to align with the text description and yields a suboptimal deformation quality. In contrast, MeshUp [29] successfully deforms the source mesh to a","cbCaibVCMNgZv8QK","https://ap.wps.com/l/cbCaibVCMNgZv8QK","pdf",23438290,1,17,"English","en",105,"# Abstract\n# Introduction\n## Challenges in Jacobian-based and CLIP-based text-guided deformation\n## PoseAlign overview: two-stage global scaling and local sculpting","[{\"question\":\"What problem does PoseAlign target in text-guided mesh deformation?\",\"answer\":\"It targets the difficulty of deforming a source mesh to satisfy text semantics while preserving the original pose, which many existing methods fail to do simultaneously.\"},{\"question\":\"How does PoseAlign structure its deformation pipeline?\",\"answer\":\"PoseAlign decomposes the task into two stages: global pose scaling and local detail sculpting.\"},{\"question\":\"What is the role of the pose-aligned SDS loss in PoseAlign?\",\"answer\":\"It adapts score distillation sampling with an attention-sharing mechanism to refine fine-grained geometry details while keeping the deformed mesh aligned with the original pose.\"}]",1784207502,43,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"posealign-sculpting-pose-consistent-meshes-via-text-guided-deformation","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/posealign-sculpting-pose-consistent-meshes-via-text-guided-deformation/85974/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-26","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does PoseAlign target in text-guided mesh deformation?","Question",{"text":75,"@type":76},"It targets the difficulty of deforming a source mesh to satisfy text semantics while preserving the original pose, which many existing methods fail to do simultaneously.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does PoseAlign structure its deformation pipeline?",{"text":80,"@type":76},"PoseAlign decomposes the task into two stages: global pose scaling and local detail sculpting.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the role of the pose-aligned SDS loss in PoseAlign?",{"text":84,"@type":76},"It adapts score distillation sampling with an attention-sharing mechanism to refine fine-grained geometry details while keeping the deformed mesh aligned with the original pose.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]