CAMM: Building Category-Agnostic and Animatable 3D Models from Monocular Videos
This reduces the work needed for creating animatable 3D models for any articulated object, addressing a domain-specific bottleneck in 3D animation.
The paper tackles the problem of creating animatable 3D models from monocular videos without prior knowledge of object shape or structure, achieving results on par with state-of-the-art 3D surface reconstruction methods across various articulated object categories.
Animating an object in 3D often requires an articulated structure, e.g. a kinematic chain or skeleton of the manipulated object with proper skinning weights, to obtain smooth movements and surface deformations. However, existing models that allow direct pose manipulations are either limited to specific object categories or built with specialized equipment. To reduce the work needed for creating animatable 3D models, we propose a novel reconstruction method that learns an animatable kinematic chain for any articulated object. Our method operates on monocular videos without prior knowledge of the object's shape or underlying structure. Our approach is on par with state-of-the-art 3D surface reconstruction methods on various articulated object categories while enabling direct pose manipulations by re-posing the learned kinematic chain.