标题:Scribble based 3D shape segmentation via weakly-supervised learning
作者:Shu Z.; Shen X.; Xin S.; Chang Q.; Feng J.; Kavan L.; Liu L.
作者机构:[Shu, Z] School of Computer and Data Engineering, Ningbo Institute of Technology, Zhejiang University, Ningbo, Zhejiang China (e-mail: shuzhenyu@gmail 更多
来源:IEEE Transactions on Visualization and Computer Graphics
出版年:2019
DOI:10.1109/TVCG.2019.2892076
关键词:3D shapes; Deep learning; Deep learning; Labeling; Scribble; Segmentation; Shape; Solid modeling; Three-dimensional displays; Training; Training data; Weakly-supervised
摘要:Shape segmentation is a fundamental problem in shape analysis. Previous research shows that prior knowledge helps to improve the segmentation accuracy and quality. However, completely labeling each 3D shape in a large training data set requires a heavy manual workload. In this paper, we propose a novel weakly-supervised algorithm for segmenting 3D shapes using deep learning. Our method jointly propagates information from scribbles to unlabeled faces and learns deep neural network parameters. Therefore, it does not rely on completely labeled training shapes and only needs a really simple and convenient scribble-based partially labeling process, instead of the extremely time-consuming and tedious fully labeling processes. Various experimental results demonstrate the proposed method's superior segmentation performance over the previous unsupervised approaches and comparable segmentation performance to the state-of-the-art fully supervised methods. IEEE
收录类别:SCOPUS
资源类型:期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85059942468&doi=10.1109%2fTVCG.2019.2892076&partnerID=40&md5=2229c4e2412c0c0112a8e7ada98b712a
TOP