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

2026-08-31

AI Summary

BLARM通过混合潜在刚性运动基元，从单目视频中生成3D物体动画，解决了高维顶点运动预测问题。

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.

Problem

• video-driven 3D mesh animation
• monocular video
• temporally coherent
• rigid motion components

Innovation

• video-driven 3D mesh animation
• latent rigid motion components
• spatial-temporal attention
• trajectory reconstruction
• motion-aware contrastive learning