H-CNN: Spatial Hashing Based CNN for 3D Shape Analysis

Abstract

We present a novel spatial hashing based data structure to facilitate 3D shape analysis using convolutional neural networks (CNNs). Our method well utilizes the sparse occupancy of 3D shape boundary and builds hierarchical hash tables for an input model under different resolutions. Based on this data structure, we design two efficient GPU algorithms namely hash2col and col2hash so that the CNN operations like convolution and pooling can be efficiently parallelized. The spatial hashing is nearly minimal, and our data structure is almost of the same size as the raw input. Compared with state-of-the-art octree-based methods, our data structure significantly reduces the memory footprint during the CNN training. As the input geometry features are more compactly packed, CNN operations also run faster with our data structure. The experiment shows that, under the same network structure, our method yields comparable or better benchmarks compared to the state-of-the-art while it has only one-third memory consumption. Such superior memory performance allows the CNN to handle high-resolution shape analysis.

arXiv comment12 pages, 9 figures

References in corpus (15)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Improving neural networks by preventing co-adaptation of feature detectors
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Geometric deep learning: going beyond Euclidean data
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• Fully Convolutional Networks for Semantic Segmentation
• ShapeNet: An Information-Rich 3D Model Repository
• O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
• Joint 2D-3D-Semantic Data for Indoor Scene Understanding
• Generative and Discriminative Voxel Modeling with Convolutional Neural Networks
• PCPNET: Learning Local Shape Properties from Raw Point Clouds
• FPNN: Field Probing Neural Networks for 3D Data
• Spatially-sparse convolutional neural networks
• Irregular Convolutional Neural Networks

Cited by in corpus (6)

• PointCNN: Convolution On $\mathcal{X}$-Transformed Points
• OctFormer: Octree-based Transformers for 3D Point Clouds
• Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations
• NFANet: A Novel Method for Weakly Supervised Water Extraction from High-Resolution Remote Sensing Imagery
• A Closer Look at Few-Shot 3D Point Cloud Classification
• 2L-LSH: A Locality-Sensitive Hash Function-Based Method For Rapid Point Cloud Indexing