NiLBS: Neural Inverse Linear Blend Skinning
This addresses a problem in computer vision and graphics for representing and deforming articulated objects, but it is incremental as it builds on existing skinning techniques without demonstrated results.
The paper tackles the problem of efficiently representing articulated objects like human bodies by introducing a neural network method to invert traditional skinning deformations, enabling pre-computation of values at rest pose for efficient querying during deformation, though empirical evaluation is deferred to future work.
In this technical report, we investigate efficient representations of articulated objects (e.g. human bodies), which is an important problem in computer vision and graphics. To deform articulated geometry, existing approaches represent objects as meshes and deform them using "skinning" techniques. The skinning operation allows a wide range of deformations to be achieved with a small number of control parameters. This paper introduces a method to invert the deformations undergone via traditional skinning techniques via a neural network parameterized by pose. The ability to invert these deformations allows values (e.g., distance function, signed distance function, occupancy) to be pre-computed at rest pose, and then efficiently queried when the character is deformed. We leave empirical evaluation of our approach to future work.