This work introduces BLARM, a feed-forward method for video-driven 3D mesh animation that produces accurate and temporally stable animations while recovering compact, interpretable motion structure from monocular video.
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.
Precise control over camera and object motion is essential for professional video production. Existing methods control objects only coarsely, through image-plane cues that are ambiguous in depth and rotation or through 3D tracks and blobs that lack complete geometry and lose consistency across viewpoint changes. We int...
Wei Cao, Hao Zhang, Vikram Voleti et al.· 1 citation
This work creates a looping 4D dynamic reconstruction which can be interactively rendered from novel viewpoints from a single non-looping 2D source video, and shows quantitatively and qualitatively that the framework enables photorealistic animation of water scenes better than prior art.
Chu-Han Chen, Yen-Chi Cheng, Ayush Saraf et al.· 0 citations
Generative models have rapidly pushed content creation be-yond 2D imagery toward dynamic 3D and 4D scene synthesis. Yet pro-ducing realistic and temporally stable 4D content from a single image is still difficult because one view provides limited structural cues and weak motion evidence. We introduce MATE4D, a framewor...
Reconstructing expressive and relightable 3D head avatars from monocular videos remains challenging in computer vision, as it requires accurate modeling of both non-rigid facial motion and illumination-dependent appearance. Existing Gaussian avatar methods commonly rely on globally coupled representations, in which Gau...
Jian-Kuo Zhao, Xiang-Yu Zhu, Ji-Jie Li et al.· arXiv.org· 0 citations
This work presents Kepler4D, a framework for future video generation through explicit 4D scene state evolution, and renders the evolving proxies into geometric controls for a pretrained video generator, separating coarse object motion from the synthesis of appearance and articulation.
Fei-Ran Wang, Bin Duan, Jun-Yi Wu et al.· 1 citation
Current controllable video generation systems often rely on 2D motion trajectories or sparse drag signals for object motion. These controls are ambiguous because the same 2D trajectory can correspond to different 3D motions, especially when the camera and objects move simultaneously. We present Generative Cinematograph...
Jia-Han Zhang, Chao-Hao Yang, N. Guruprasad et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.