Unsupervised Learning of Global Registration of Temporal Sequence of Point Clouds
This work addresses the challenge of global registration for point cloud sequences, which is important for applications like robotics and 3D reconstruction, but it appears incremental as it builds on existing deep learning techniques with a focus on temporal aspects.
The paper tackles the problem of globally aligning a sequence of 2D or 3D point clouds by introducing an unsupervised deep learning method that uses a novel Spatio-Temporal REPresentation (STREP) feature, and it demonstrates improved performance over other techniques by incorporating temporal information in feature learning.
Global registration of point clouds aims to find an optimal alignment of a sequence of 2D or 3D point sets. In this paper, we present a novel method that takes advantage of current deep learning techniques for unsupervised learning of global registration from a temporal sequence of point clouds. Our key novelty is that we introduce a deep Spatio-Temporal REPresentation (STREP) feature, which describes the geometric essence of both temporal and spatial relationship of the sequence of point clouds acquired with sensors in an unknown environment. In contrast to the previous practice that treats each time step (pair-wise registration) individually, our unsupervised model starts with optimizing a sequence of latent STREP feature, which is then decoded to a temporally and spatially continuous sequence of geometric transformations to globally align multiple point clouds. We have evaluated our proposed approach over both simulated 2D and real 3D datasets and the experimental results demonstrate that our method can beat other techniques by taking into account the temporal information in deep feature learning.