3D Shape Segmentation via Shape Fully Convolutional Networks

TL;DR

This paper introduces Shape Fully Convolutional Networks (SFCN), a novel architecture for 3D shape segmentation that adapts convolutional operations to graph-structured data, enabling effective segmentation of diverse shape datasets.

Contribution

The paper proposes a new graph-based fully convolutional network architecture for 3D shape segmentation, including novel graph convolution and pooling operations, and demonstrates its effectiveness on mixed shape datasets.

Findings

Effective segmentation of mixed shape datasets

Successful adaptation of FCN architecture to graph-structured data

High accuracy in shape segmentation tasks

Abstract

We desgin a novel fully convolutional network architecture for shapes, denoted by Shape Fully Convolutional Networks (SFCN). 3D shapes are represented as graph structures in the SFCN architecture, based on novel graph convolution and pooling operations, which are similar to convolution and pooling operations used on images. Meanwhile, to build our SFCN architecture in the original image segmentation fully convolutional network (FCN) architecture, we also design and implement a generating operation} with bridging function. This ensures that the convolution and pooling operation we have designed can be successfully applied in the original FCN architecture. In this paper, we also present a new shape segmentation approach based on SFCN. Furthermore, we allow more general and challenging input, such as mixed datasets of different categories of shapes} which can prove the ability of our generalisation. In our approach, SFCNs are trained triangles-to-triangles by using three low-level geometric features as input. Finally, the feature voting-based multi-label graph cuts is adopted to optimise the segmentation results obtained by SFCN prediction. The experiment results show that our method can effectively learn and predict mixed shape datasets of either similar or different characteristics, and achieve excellent segmentation results.