O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
This work addresses efficiency issues in 3D shape analysis for computer vision and graphics applications, offering a novel method but with incremental improvements over existing 3D CNN solutions.
The authors tackled the problem of high memory and computational costs in 3D shape analysis by proposing O-CNN, an octree-based convolutional neural network, which reduces costs to quadratic growth with octree depth and achieves competitive performance in tasks like object classification, shape retrieval, and segmentation.
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 analysis tasks, including object classification, shape retrieval, and shape segmentation.