Segmentation Improves 3D Object Classification in Graph Convolutional Networks
C. Holzhüter, F. Teich, und F. Wörgötter. International Conference on Computer Vision Theory and Applications (VISAPP), Seite 290--298. (2022)
3D object classification is involved in many computer vision pipelines such as autonomous driving or robotics. However, the irregular format of 3D data makes it challenging to develop suitable deep learning architectures. This paper proposes CompointNet, a graph convolutional network architecture, which performs 3D object classification by means of part decomposition. Our model consumes a 3D point cloud in the form of a part graph which is constructed from segmented 3D shapes. The model learns a global descriptor by hierarchically aggregating neighbourhood information using simple graph convolutions. To capture both local and global information, a global classification method processing each point separately is combined with our part graph based approach into a hybrid version of CompointNet. We compare our approach to several state-of-the art methods and demonstrate competitive performance. Particularly, in terms of per class accuracy, our hybrid approach outperforms the compared methods. The proposed hybrid variants achieve a high classification accuracy, while being much more efficient than those benchmark models with a comparable performance. The conducted experiments show that part based approaches levering structural information about a 3D object, indeed, can improve the classification performance of 3D deep learning models.
