A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting

[2604.13427] A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting Skip to main content Search Submit Donate Log in Computer Science > Graphics arXiv:2604.13427 (cs) [Submitted on 15 Apr 2026 ( v1 ), last revised 10 Sep 2026 (this version, v3)] Title: A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting Authors: Junlin Li , Xinhao Song , Siqi Wang , Haibin Huang , Yili Zhao View PDF HTML (experimental) Abstract: Text-driven motion editing and intra-structural retargeting, where skeletons share topology but may differ in bone lengths and rest pose, are traditionally handled by fragmented pipelines with incompatible inputs and representations: editing relies on specialized generative steering, while retargeting is deferred to geometric post-processing. We present a unified conditional-flow framework that casts generation, semantic editing, and intra-structural retargeting as condition-modulated transport within one text- and skeleton-conditioned rectified-flow model. Under this formulation, editing changes the semantic condition while preserving skeletal structure, whereas retargeting changes the skeletal condition while preserving motion semantics. This makes FlowEdit-style transport a unified inference rule for motion manipulation rather than a task-specific editor. To instantiate this for articulated 3D motion, we develop a text- and skeleton-conditioned rectified-flow transformer. The model uses per-joint tokenization and explicit joint self-attention to capture spatial kinematic dependencies. We further inject text conditions at both joint and frame levels, while residual multi-condition classifier-free guidance balances text adherence and skeletal conformity. Experiments on SnapMoGen and a multi-character Mixamo subset show that one trained model supports text-to-motion generation, zero-shot editing, and zero-shot intra-structural retargeting without task-specific fine-tuning. This unified framework replaces separate pipelines with a single conditional motion transport model while keeping the same-topology retargeting scope explicit. Comments: 16 pages, includes supplementary material; Project Page: this https URL Subjects: Graphics (cs.GR) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) ACM classes: I.3.7; I.2.6 Cite as: arXiv:2604.13427 [cs.GR] (or arXiv:2604.13427v3 [cs.GR] for this version) https://doi.org/10.48550/arXiv.2604.13427 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yili Zhao [ view email ] [v1] Wed, 15 Apr 2026 02:53:07 UTC (3,053 KB) [v2] Wed, 26 Aug 2026 23:26:12 UTC (9,742 KB) [v3] Thu, 10 Sep 2026 23:14:54 UTC (9,742 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: cs.GR < prev | next > new | recent | 2026-04 Change to browse by: cs cs.AI cs.CV References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting#674369
• Generative Animations: A Multi-Model Pipeline for Prompt-Driven Motion Synthesis#229541
• FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control#617960
• FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control#617460
• FloodDiffusion 2: Efficient and Path Controllable Streaming Motion Generation#1117879