PIG-Net: Inception based Deep Learning Architecture for 3D Point Cloud Segmentation
arXiv:2101.11987 · doi:10.1016/j.cag.2021.01.004
Abstract
Point clouds, being the simple and compact representation of surface geometry of 3D objects, have gained increasing popularity with the evolution of deep learning networks for classification and segmentation tasks. Unlike human, teaching the machine to analyze the segments of an object is a challenging task and quite essential in various machine vision applications. In this paper, we address the problem of segmentation and labelling of the 3D point clouds by proposing a inception based deep network architecture called PIG-Net, that effectively characterizes the local and global geometric details of the point clouds. In PIG-Net, the local features are extracted from the transformed input points using the proposed inception layers and then aligned by feature transform. These local features are aggregated using the global average pooling layer to obtain the global features. Finally, feed the concatenated local and global features to the convolution layers for segmenting the 3D point clouds. We perform an exhaustive experimental analysis of the PIG-Net architecture on two state-of-the-art datasets, namely, ShapeNet [1] and PartNet [2]. We evaluate the effectiveness of our network by performing ablation study.
11 pages, 5 Figures, 6 Tables, Accepted in Computers & Graphics Journal 2021
References in corpus (13)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- Fully Convolutional Networks for Semantic Segmentation
- Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning
- O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
- Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
- RGB-D Object Detection and Semantic Segmentation for Autonomous Manipulation in Clutter
- Learning Part Boundaries from 3D Point Clouds
- Multiresolution Tree Networks for 3D Point Cloud Processing
- Learning Gaussian Instance Segmentation in Point Clouds
- Associatively Segmenting Instances and Semantics in Point Clouds
- 3D Shape Segmentation via Shape Fully Convolutional Networks
- Few-shot 3D Point Cloud Semantic Segmentation