BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives

Hugging Face Daily Papers Papers

Summary

BLARM is a feed-forward method for animating 3D meshes from monocular video by blending latent rigid motion primitives, enabling temporally coherent animations without explicit rigs.

We introduce BLARM, a feed-forward method for video-driven 3D mesh animation. Given a monocular video and a static object mesh, BLARM predicts a temporally coherent animated mesh whose motion follows the video. Rather than relying on explicit rigs or directly regressing high-dimensional vertex motion, we represent animation using a compact set of learned, time-varying rigid motion components and time-invariant vertex-to-component skinning weights. This yields a low-dimensional deformation space without requiring skeletons, cages, skinning weights, or rig annotations. Our architecture conditions geometry-derived deformation latents on video features through factorized spatial-temporal attention, then decodes rigid transformations blended by predicted skinning weights. Trained with trajectory reconstruction, entropy regularization, and motion-aware contrastive learning, BLARM produces accurate and temporally stable animations while recovering compact, interpretable motion structure from monocular video.
Original Article
View Cached Full Text

Cached at: 09/01/26, 11:54 AM

Paper page - BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives

Source: https://huggingface.co/papers/2608.31113

Abstract

BLARM predicts temporally coherent 3D mesh animations from monocular video using learned rigid motion components and skinning weights without explicit rigs.

We introduce BLARM, afeed-forwardmethod forvideo-driven 3D mesh animation. Given a monocular video and a static object mesh, BLARM predicts a temporally coherent animated mesh whose motion follows the video. Rather than relying on explicit rigs or directly regressing high-dimensional vertex motion, we represent animation using a compact set of learned, time-varyingrigid motion componentsand time-invariant vertex-to-componentskinning weights. This yields a low-dimensional deformation space without requiring skeletons, cages,skinning weights, or rig annotations. Our architecture conditions geometry-deriveddeformation latentson video features throughfactorized spatial-temporal attention, then decodes rigid transformations blended by predictedskinning weights. Trained withtrajectory reconstruction,entropy regularization, andmotion-aware contrastive learning, BLARM produces accurate and temporally stable animations while recovering compact, interpretable motion structure from monocular video.

View arXiv pageView PDFAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.31113 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.31113 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.31113 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

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.