One Framework to Register Them All: PointNet Encoding for Point Cloud Alignment
This work addresses pose misalignment issues in point cloud applications like 3D reconstruction and tracking, offering a novel framework that is robust and efficient, though it builds incrementally on existing PointNet methods.
The paper tackles the problem of point cloud registration by using PointNet encoding to align template and source point clouds, avoiding computationally expensive correspondence finding steps, and demonstrates robustness to noise, initial misalignment, and partial data in simulations and real-world experiments.
PointNet has recently emerged as a popular representation for unstructured point cloud data, allowing application of deep learning to tasks such as object detection, segmentation and shape completion. However, recent works in literature have shown the sensitivity of the PointNet representation to pose misalignment. This paper presents a novel framework that uses PointNet encoding to align point clouds and perform registration for applications such as 3D reconstruction, tracking and pose estimation. We develop a framework that compares PointNet features of template and source point clouds to find the transformation that aligns them accurately. In doing so, we avoid computationally expensive correspondence finding steps, that are central to popular registration methods such as ICP and its variants. Depending on the prior information about the shape of the object formed by the point clouds, our framework can produce approaches that are shape specific or general to unseen shapes. Our framework produces approaches that are robust to noise and initial misalignment in data and work robustly with sparse as well as partial point clouds. We perform extensive simulation and real-world experiments to validate the efficacy of our approach and compare the performance with state-of-art approaches. Code is available at https://github.com/vinits5/pointnet-registrationframework.