MARNet: Multi-Abstraction Refinement Network for 3D Point Cloud Analysis

Abstract

Representation learning from 3D point clouds is challenging due to their inherent nature of permutation invariance and irregular distribution in space. Existing deep learning methods follow a hierarchical feature extraction paradigm in which high-level abstract features are derived from low-level features. However, they fail to exploit different granularity of information due to the limited interaction between these features. To this end, we propose Multi-Abstraction Refinement Network (MARNet) that ensures an effective exchange of information between multi-level features to gain local and global contextual cues while effectively preserving them till the final layer. We empirically show the effectiveness of MARNet in terms of state-of-the-art results on two challenging tasks: Shape classification and Coarse-to-fine grained semantic segmentation. MARNet significantly improves the classification performance by 2% over the baseline and outperforms the state-of-the-art methods on semantic segmentation task.

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Densely Connected Convolutional Networks
• Scalability in Perception for Autonomous Driving: Waymo Open Dataset
• Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
• PointConv: Deep Convolutional Networks on 3D Point Clouds
• Local Spectral Graph Convolution for Point Set Feature Learning
• Multiresolution Tree Networks for 3D Point Cloud Processing
• Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition
• OctNet: Learning Deep 3D Representations at High Resolutions
• Interpolated Convolutional Networks for 3D Point Cloud Understanding
• Octree guided CNN with Spherical Kernels for 3D Point Clouds
• Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
• Hypergraph Neural Networks