Peng-Shuai Wang, Yang Liu, Yu-Xiao Guo, Chun-Yu Sun, Xin Tong
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.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Semantic Segmentation | ScanNet | test mIoU | 76.2 | O-CNN |
| Semantic Segmentation | ScanNet | val mIoU | 74 | O-CNN |
| 3D | ModelNet40 | Classification Accuracy | 89.9 | O-CNN(6) |
| Shape Representation Of 3D Point Clouds | ModelNet40 | Classification Accuracy | 89.9 | O-CNN(6) |
| 3D Object Classification | ModelNet40 | Classification Accuracy | 89.9 | O-CNN(6) |
| 3D Point Cloud Classification | ModelNet40 | Classification Accuracy | 89.9 | O-CNN(6) |
| 3D Classification | ModelNet40 | Classification Accuracy | 89.9 | O-CNN(6) |
| 10-shot image generation | ScanNet | test mIoU | 76.2 | O-CNN |
| 10-shot image generation | ScanNet | val mIoU | 74 | O-CNN |
| 3D Point Cloud Reconstruction | ModelNet40 | Classification Accuracy | 89.9 | O-CNN(6) |