Learning a 3D descriptor for cross-source point cloud registration from synthetic data
This addresses the need for robust point cloud registration across diverse sensors, which is incremental as it builds on existing descriptor methods but extends to cross-source scenarios.
The paper tackles the problem of registering 3D point clouds from different sensors, which is challenging due to variations in density, noise, and viewpoints, by learning a 3D descriptor from synthetic data; the result is a method that successfully aligns cross-source point clouds and outperforms state-of-the-art approaches.
As the development of 3D sensors, registration of 3D data (e.g. point cloud) coming from different kind of sensor is dispensable and shows great demanding. However, point cloud registration between different sensors is challenging because of the variant of density, missing data, different viewpoint, noise and outliers, and geometric transformation. In this paper, we propose a method to learn a 3D descriptor for finding the correspondent relations between these challenging point clouds. To train the deep learning framework, we use synthetic 3D point cloud as input. Starting from synthetic dataset, we use region-based sampling method to select reasonable, large and diverse training samples from synthetic samples. Then, we use data augmentation to extend our network be robust to rotation transformation. We focus our work on more general cases that point clouds coming from different sensors, named cross-source point cloud. The experiments show that our descriptor is not only able to generalize to new scenes, but also generalize to different sensors. The results demonstrate that the proposed method successfully aligns two 3D cross-source point clouds which outperforms state-of-the-art method.