Motion4Motion: Motion Transfer Across Subjects at Inference

Hugging Face Daily Papers Papers
motion-transfer video-animation training-free cross-species motion-flow inference-time character-animation

Summary

Motion4Motion is a training-free motion transfer framework that models motion flow from a video instead of relying on skeleton structures, enabling motion transfer across diverse species (e.g., humans to animals) at inference time.

This work explores the motion transfer from one video to another, which is crucial in animation for diverse characters. Previously, video motion transfer has been largely explored between human and human-like characters, enabling a lot of applications in digital creation. However, these approaches encounter a main limitation. Specifically, related technical pipelines heavily rely on a predefined human skeleton structure and accordingly require skeleton-conditional model training. On the one hand, these methods are difficult to generalize to diverse characters, such as animals from different species, while preserving their unique motion styles. On the other hand, labeled data in diverse skeletons is limited, which additionally restricts the large-scale training for the task. In this paper, we jump out of the skeleton-based motion transfer framework and propose a training-free motion transfer framework, named Motion4Motion. Motion4Motionmodels the motion flow of the character in a video instead of skeletons, which makes motion transfer across species easier. Extensive experimental results and novel applications show our methods outperform baselines impressively. Project page is available at https://lhchen.top/Motion4Motion.
Original Article
View Cached Full Text

Cached at: 07/14/26, 04:12 AM

Paper page - Motion4Motion: Motion Transfer Across Subjects at Inference

Source: https://huggingface.co/papers/2607.11644

Abstract

Thisworkexploresthemotiontransferfromonevideotoanother,whichiscrucialinanimationfordiversecharacters.Previously,videomotiontransferhasbeenlargelyexploredbetweenhumanandhuman-likecharacters,enablingalotofapplicationsindigitalcreation.However,theseapproachesencounteramainlimitation.Specifically,relatedtechnicalpipelinesheavilyrelyonapredefinedhumanskeletonstructureandaccordinglyrequireskeleton-conditionalmodeltraining.Ontheonehand,thesemethodsaredifficulttogeneralizetodiversecharacters,suchasanimalsfromdifferentspecies,whilepreservingtheiruniquemotionstyles.Ontheotherhand,labeleddataindiverseskeletonsislimited,whichadditionallyrestrictsthelarge-scaletrainingforthetask.Inthispaper,wejumpoutoftheskeleton-basedmotiontransferframeworkandproposeatraining-freemotiontransferframework,namedMotion4Motion.Motion4Motionmodelsthemotionflowofthecharacterinavideoinsteadofskeletons,whichmakesmotiontransferacrossspecieseasier.Extensiveexperimentalresultsandnovelapplicationsshowourmethodsoutperformbaselinesimpressively.Projectpageisavailableathttps://lhchen.top/Motion4Motion.

View arXiv pageView PDFProject pageAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.11644 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.11644 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.11644 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Motion

Product Hunt

Motion is a video agent designed to create tasteful motion design.

MolmoMotion: Language-guided 3D motion forecasting

Hugging Face Blog

MolmoMotion is a new language-guided 3D motion forecasting model that predicts future 3D point trajectories from video frames and action descriptions, achieving stronger performance than existing methods. Alongside the model, a large dataset (MolmoMotion-1M) and a benchmark (PointMotionBench) are released.

AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild

Hugging Face Daily Papers

AnyMo is a geometry-aware framework for setup-agnostic human motion modeling using physics-grounded IMU simulation and graph encoding, achieving significant improvements in zero-shot activity recognition, cross-modal retrieval, and motion captioning across multiple datasets.