NASA: Neural Articulated Shape Approximation
This provides a more efficient framework for representing articulated deformable objects in computer vision and graphics, though it appears incremental as it builds on existing neural and shape approximation methods.
The paper tackles the problem of efficiently representing articulated objects like human bodies by introducing neural articulated shape approximation (NASA), which uses neural indicator functions conditioned on pose to simplify occupancy testing and avoid mesh complexity and water-tightness issues.
Efficient representation of articulated objects such as human bodies is an important problem in computer vision and graphics. To efficiently simulate deformation, existing approaches represent 3D objects using polygonal meshes and deform them using skinning techniques. This paper introduces neural articulated shape approximation (NASA), an alternative framework that enables efficient representation of articulated deformable objects using neural indicator functions that are conditioned on pose. Occupancy testing using NASA is straightforward, circumventing the complexity of meshes and the issue of water-tightness. We demonstrate the effectiveness of NASA for 3D tracking applications, and discuss other potential extensions.