Abstract
Due to the irregularity and inconsistency of 3D point clouds, it is difficult to extract features directly from them. Existing methods usually extract point features independently and then use the max-pooling operation to aggregate local features, which limits the feature representation capability of their models. In this work, we design a novel spatial-related correlation path, which considers both spatial information and point correlations, to preserve high dimensional features, thereby capturing fine-detail information and long-distance context of the point cloud. We further propose a new network to aggregate the spatial aware correlations with point-wise features and global features in a learnable way. The experimental results show that our method can achieve better performance than the state-of-the-art approaches on challenging datasets. We can achieve 0.934 accuracy on ModelNet40 dataset and 0.875 mean IoU (Intersection over Union) on ShapeNet dataset with only about 2.42 million parameters.
Highlights
Object recognition is one of the most classical and fundamental problems in computer vision. It is very useful as a preprocessing step in various computer vision applications, such as image classification and segmentation [1], [2], 3D reconstruction [3], [4], object detection [5] and pose estimation [6]
The contributions of the proposed method are summarized as follows: 1. We introduce a SRC path which is capable of modeling point correlations both in feature space and in spatial space
Unlike previous methods that used shared multi-layer perceptron (MLP) and symmetric functions to extract local features, we focused on modeling point correlations with long range connections, preserving detailed information
Summary
Object recognition is one of the most classical and fundamental problems in computer vision. It is very useful as a preprocessing step in various computer vision applications, such as image classification and segmentation [1], [2], 3D reconstruction [3], [4], object detection [5] and pose estimation [6]. To deal with the problem, some alternative approaches project 3D point sets into volumetric grids or multiple 2D image views to take advantage of using 3D convolution. In this case, it will lead to high computational cost and information loss
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
