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

arXiv:2608.31113v1 Announce Type: new Abstract: 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.

Related

• MeshLAM: Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction
• RigPAPR: Rig-Based Animation of Static Neural Point Clouds from a Fixed-Viewpoint Video
• Artic-O: End-to-End Articulated Object Reconstruction via Latent Geometry Learning
• D-Prism: Differentiable Primitives for Structured Dynamic Modeling
• Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations

Source: arXiv cs.CV | 2026-09-01