O-CNN: Octree-based Convolutional Neural Networks For 3D Shape Analysis
2017 · Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, et al.
Abstract
We present O-CNN, an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis. Built upon the octree representation of 3D shapes, our method takes the average normal vectors of a 3D model sampled in the finest leaf octants as input and performs 3D CNN operations on the octants occupied by the 3D shape surface. We design a novel octree data structure to efficiently store the octant information and CNN features into the graphics memory and execute the entire O-CNN training and evaluation on the GPU. O-CNN supports various CNN structures and works for 3D shapes in different representations. By restraining the computations on the octants occupied by 3D surfaces, the memory and computational costs of the O-CNN grow quadratically as the depth of the octree increases, which makes the 3D CNN feasible for high-resolution 3D models. We compare the performance of the O-CNN with other existing 3D CNN solutions and demonstrate the efficiency and efficacy of O-CNN in three shape analysi
Authors
(none)
Tags
Stats
Related papers
- Unsupervised Detection Of Distinctive Regions On 3D Shapes (2019)7.50
- Escape From Cells: Deep Kd-networks For The Recognition Of 3D Point Cloud Models (2017)21.60
- Risa-net: Rotation-invariant Structure-aware Network For Fine-grained 3D Shape Retrieval (2020)5.48
- Pvrnet: Point-view Relation Neural Network For 3D Shape Recognition (2018)13.11
- A Convolutional Architecture For 3D Model Embedding (2021)0.00
- Spnet: Deep 3D Object Classification And Retrieval Using Stereographic Projection (2018)10.74
- MVTN: Multi-view Transformation Network For 3D Shape Recognition (2020)21.44
- Generalizing Single-view 3D Shape Retrieval To Occlusions And Unseen Objects (2023)5.24