Pointwise Attention-Based Atrous Convolutional Neural Networks
This work addresses 3D semantic segmentation for robotic applications, offering an incremental improvement in efficiency.
The paper tackles the problem of 3D semantic segmentation from point clouds by proposing a pointwise attention-based atrous convolutional neural network to efficiently handle large numbers of points and incorporate context, achieving reasonable performance compared to state-of-the-art models with fewer parameters.
With the rapid progress of deep convolutional neural networks, in almost all robotic applications, the availability of 3D point clouds improves the accuracy of 3D semantic segmentation methods. Rendering of these irregular, unstructured, and unordered 3D points to 2D images from multiple viewpoints imposes some issues such as loss of information due to 3D to 2D projection, discretizing artifacts, and high computational costs. To efficiently deal with a large number of points and incorporate more context of each point, a pointwise attention-based atrous convolutional neural network architecture is proposed. It focuses on salient 3D feature points among all feature maps while considering outstanding contextual information via spatial channel-wise attention modules. The proposed model has been evaluated on the two most important 3D point cloud datasets for the 3D semantic segmentation task. It achieves a reasonable performance compared to state-of-the-art models in terms of accuracy, with a much smaller number of parameters.