CloudWalker: Random walks for 3D point cloud shape analysis
This addresses the problem of 3D shape analysis for applications like computer vision and robotics, presenting a novel approach rather than an incremental improvement.
The paper tackles the challenge of analyzing 3D point clouds with irregular structures by proposing CloudWalker, a method that uses random walks to impose structure and learn representations, achieving state-of-the-art results in classification and retrieval tasks.
Point clouds are gaining prominence as a method for representing 3D shapes, but their irregular structure poses a challenge for deep learning methods. In this paper we propose CloudWalker, a novel method for learning 3D shapes using random walks. Previous works attempt to adapt Convolutional Neural Networks (CNNs) or impose a grid or mesh structure to 3D point clouds. This work presents a different approach for representing and learning the shape from a given point set. The key idea is to impose structure on the point set by multiple random walks through the cloud for exploring different regions of the 3D object. Then we learn a per-point and per-walk representation and aggregate multiple walk predictions at inference. Our approach achieves state-of-the-art results for two 3D shape analysis tasks: classification and retrieval.