3D Shape Segmentation via Shape Fully Convolutional Networks

02/28/2017
by   Pengyu Wang, et al.
0

We propose 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.

READ FULL TEXT

page 1

page 6

page 8

research
11/17/2017

Towards dense volumetric pancreas segmentation in CT using 3D fully convolutional networks

Pancreas segmentation in computed tomography imaging has been historical...
research
03/29/2020

Superpixel Segmentation with Fully Convolutional Networks

In computer vision, superpixels have been widely used as an effective wa...
research
12/08/2016

3D Shape Segmentation with Projective Convolutional Networks

This paper introduces a deep architecture for segmenting 3D objects into...
research
05/10/2019

Semantic Segmentation of Seismic Images

Almost all work to understand Earth's subsurface on a large scale relies...
research
11/14/2016

Can fully convolutional networks perform well for general image restoration problems?

We present a fully convolutional network(FCN) based approach for color i...
research
06/21/2020

FilterNet: A Neighborhood Relationship Enhanced Fully Convolutional Network for Calf Muscle Compartment Segmentation

Automated segmentation of individual calf muscle compartments from 3D ma...

Please sign up or login with your details

Forgot password? Click here to reset