3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks
This addresses the problem of memory inefficiency in 3D point cloud processing for computer vision applications, though it is incremental as it builds on existing grid and Fisher vector methods.
The paper tackled the challenge of representing irregular 3D point clouds for deep learning by proposing a hybrid 3D Modified Fisher Vector representation, achieving competitive or better performance than state-of-the-art methods on benchmark datasets.
The point cloud is gaining prominence as a method for representing 3D shapes, but its irregular format poses a challenge for deep learning methods. The common solution of transforming the data into a 3D voxel grid introduces its own challenges, mainly large memory size. In this paper we propose a novel 3D point cloud representation called 3D Modified Fisher Vectors (3DmFV). Our representation is hybrid as it combines the discrete structure of a grid with continuous generalization of Fisher vectors, in a compact and computationally efficient way. Using the grid enables us to design a new CNN architecture for point cloud classification and part segmentation. In a series of experiments we demonstrate competitive performance or even better than state-of-the-art on challenging benchmark datasets.