Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction
This work addresses the problem of robust non-rigid 3D reconstruction and deformation tracking for general objects, offering significant improvements over existing methods.
This paper introduces Neural Deformation Graphs for globally-consistent non-rigid 3D reconstruction and deformation tracking. The method implicitly models a deformation graph via a neural network, which is optimized using self-supervised training on depth camera observations, resulting in 64% improved reconstruction and 62% improved deformation tracking performance.
We introduce Neural Deformation Graphs for globally-consistent deformation tracking and 3D reconstruction of non-rigid objects. Specifically, we implicitly model a deformation graph via a deep neural network. This neural deformation graph does not rely on any object-specific structure and, thus, can be applied to general non-rigid deformation tracking. Our method globally optimizes this neural graph on a given sequence of depth camera observations of a non-rigidly moving object. Based on explicit viewpoint consistency as well as inter-frame graph and surface consistency constraints, the underlying network is trained in a self-supervised fashion. We additionally optimize for the geometry of the object with an implicit deformable multi-MLP shape representation. Our approach does not assume sequential input data, thus enabling robust tracking of fast motions or even temporally disconnected recordings. Our experiments demonstrate that our Neural Deformation Graphs outperform state-of-the-art non-rigid reconstruction approaches both qualitatively and quantitatively, with 64% improved reconstruction and 62% improved deformation tracking performance.