Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes

Abstract

We present an Adaptive Octree-based Convolutional Neural Network (Adaptive O-CNN) for efficient 3D shape encoding and decoding. Different from volumetric-based or octree-based CNN methods that represent a 3D shape with voxels in the same resolution, our method represents a 3D shape adaptively with octants at different levels and models the 3D shape within each octant with a planar patch. Based on this adaptive patch-based representation, we propose an Adaptive O-CNN encoder and decoder for encoding and decoding 3D shapes. The Adaptive O-CNN encoder takes the planar patch normal and displacement as input and performs 3D convolutions only at the octants at each level, while the Adaptive O-CNN decoder infers the shape occupancy and subdivision status of octants at each level and estimates the best plane normal and displacement for each leaf octant. As a general framework for 3D shape analysis and generation, the Adaptive O-CNN not only reduces the memory and computational cost, but also offers better shape generation capability than the existing 3D-CNN approaches. We validate Adaptive O-CNN in terms of efficiency and effectiveness on different shape analysis and generation tasks, including shape classification, 3D autoencoding, shape prediction from a single image, and shape completion for noisy and incomplete point clouds.

References in corpus (7)

• Auto-Encoding Variational Bayes
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Geometric deep learning: going beyond Euclidean data
• ShapeNet: An Information-Rich 3D Model Repository
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
• Generative and Discriminative Voxel Modeling with Convolutional Neural Networks

Cited by in corpus (9)

• Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era
• Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
• DNF-Net: a Deep Normal Filtering Network for Mesh Denoising
• Laplacian2Mesh: Laplacian-Based Mesh Understanding
• PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution
• Learning Part Boundaries from 3D Point Clouds
• Learning Mesh Representations via Binary Space Partitioning Tree Networks
• Intelligent Generation of Graphical Game Assets: A Conceptual Framework and Systematic Review of the State of the Art
• Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitives