DPDist : Comparing Point Clouds Using Deep Point Cloud Distance
This addresses the challenge of accurate point cloud comparison for applications like 3D object recognition and registration, though it appears incremental as it builds on existing distance metrics with a novel deep learning twist.
The paper tackled the problem of comparing point clouds by introducing DPDist, a deep learning method that measures distance between points and estimated surfaces, showing significant improvements over existing distances like Chamfer and Earth mover's distance in tasks such as object comparison and registration.
We introduce a new deep learning method for point cloud comparison. Our approach, named Deep Point Cloud Distance (DPDist), measures the distance between the points in one cloud and the estimated surface from which the other point cloud is sampled. The surface is estimated locally and efficiently using the 3D modified Fisher vector representation. The local representation reduces the complexity of the surface, enabling efficient and effective learning, which generalizes well between object categories. We test the proposed distance in challenging tasks, such as similar object comparison and registration, and show that it provides significant improvements over commonly used distances such as Chamfer distance, Earth mover's distance, and others.