| title | BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives |
|---|---|
| authors | Pradyumn Goyal, Yizhak Ben-Shabat, Hsueh-Ti Derek Liu, Haomiao Jiang, Snehasish Mukherjee, Kyle Spence, Mark Stauber, Evangelos Kalogerakis, Yunze Zeng |
| date | 2026-08-31 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2608.31113 |
| affiliation | Roblox Corporation |
| upvotes | 3 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| 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. |
cite
@misc{goyal2026blarm,
title={BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives},
author={Pradyumn Goyal and Yizhak Ben-Shabat and Hsueh-Ti Derek Liu and Haomiao Jiang and Snehasish Mukherjee and Kyle Spence and Mark Stauber and Evangelos Kalogerakis and Yunze Zeng},
year={2026},
eprint={2608.31113},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2608.31113}
}