A Survey on Deep Geometry Learning: From a Representation Perspective

Abstract

Researchers have now achieved great success on dealing with 2D images using deep learning. In recent years, 3D computer vision and Geometry Deep Learning gain more and more attention. Many advanced techniques for 3D shapes have been proposed for different applications. Unlike 2D images, which can be uniformly represented by regular grids of pixels, 3D shapes have various representations, such as depth and multi-view images, voxel-based representation, point-based representation, mesh-based representation, implicit surface representation, etc. However, the performance for different applications largely depends on the representation used, and there is no unique representation that works well for all applications. Therefore, in this survey, we review recent development in deep learning for 3D geometry from a representation perspective, summarizing the advantages and disadvantages of different representations in different applications. We also present existing datasets in these representations and further discuss future research directions.

References in corpus (20)

• Semi-Supervised Classification with Graph Convolutional Networks
• Geometric deep learning: going beyond Euclidean data
• Spectral Networks and Locally Connected Networks on Graphs
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• Deep Convolutional Networks on Graph-Structured Data
• MeshCNN: A Network with an Edge
• Autoencoding beyond pixels using a learned similarity metric
• ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes
• FPNN: Field Probing Neural Networks for 3D Data
• Learning to Infer Implicit Surfaces without 3D Supervision
• PolyGen: An Autoregressive Generative Model of 3D Meshes
• PRS-Net: Planar Reflective Symmetry Detection Net for 3D Models
• PFCNN: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames
• NASA: Neural Articulated Shape Approximation
• BSP-Net: Generating Compact Meshes via Binary Space Partitioning
• LaplacianNet: Learning on 3D Meshes with Laplacian Encoding and Pooling
• PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes
• Local Deep Implicit Functions for 3D Shape
• Mesh Variational Autoencoders with Edge Contraction Pooling