CAMO: Category-Agnostic 3D Motion Transfer from Monocular 2D Videos
By: Taeyeon Kim , Youngju Na , Jumin Lee and more
Potential Business Impact:
Moves real-world actions onto 3D objects.
Motion transfer from 2D videos to 3D assets is a challenging problem, due to inherent pose ambiguities and diverse object shapes, often requiring category-specific parametric templates. We propose CAMO, a category-agnostic framework that transfers motion to diverse target meshes directly from monocular 2D videos without relying on predefined templates or explicit 3D supervision. The core of CAMO is a morphology-parameterized articulated 3D Gaussian splatting model combined with dense semantic correspondences to jointly adapt shape and pose through optimization. This approach effectively alleviates shape-pose ambiguities, enabling visually faithful motion transfer for diverse categories. Experimental results demonstrate superior motion accuracy, efficiency, and visual coherence compared to existing methods, significantly advancing motion transfer in varied object categories and casual video scenarios.
Similar Papers
MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos
CV and Pattern Recognition
Lets any object in a video move like a character.
Track and Caption Any Motion: Query-Free Motion Discovery and Description in Videos
CV and Pattern Recognition
Lets computers describe what's happening in videos.
Gaussian See, Gaussian Do: Semantic 3D Motion Transfer from Multiview Video
CV and Pattern Recognition
Makes 3D objects dance like real people.