Structured 2D Representation of 3D Data for Shape Processing
This addresses the challenge of applying efficient 2D methods to 3D data for researchers in computer vision and graphics, though it is incremental in adapting existing techniques.
The paper tackles the problem of processing 3D shapes by representing them as structured 2D descriptors, enabling the use of 2D CNNs for tasks like classification and segmentation, achieving 99.7% accuracy on ModelNet40, which significantly improves over previous state-of-the-art.
We represent 3D shape by structured 2D representations of fixed length making it feasible to apply well investigated 2D convolutional neural networks (CNN) for both discriminative and geometric tasks on 3D shapes. We first provide a general introduction to such structured descriptors, analyze their different forms and show how a simple 2D CNN can be used to achieve good classification result. With a specialized classification network for images and our structured representation, we achieve the classification accuracy of 99.7\% in the ModelNet40 test set - improving the previous state-of-the-art by a large margin. We finally provide a novel framework for performing the geometric task of 3D segmentation using 2D CNNs and the structured representation - concluding the utility of such descriptors for both discriminative and geometric tasks.