期刊
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
卷 26, 期 8, 页码 2671-2682出版社
IEEE COMPUTER SOC
DOI: 10.1109/TVCG.2019.2892076
关键词
Shape; Three-dimensional displays; Training; Labeling; Training data; Solid modeling; Deep learning; 3D shapes; segmentation; scribble; weakly-supervised; deep learning
资金
- National Natural Science Foundation of China [61872321, 61672482, 11626253, 61732015, 61772016, 61572022]
- National Science Foundation [IIS-1617172, IIS-1622360]
- Natural Science Foundation of Zhejiang Province [LY17F020018]
- Natural Science Foundation of Ningbo City [2018A610161]
- Ningbo Leader and Top-notch Talent Training Project [NBLJ201801010]
- Ningbo Innovative Team: The intelligent big data engineering application for life and health [2016C11024]
- Fundamental Research Funds of Shandong University
- Open Project Program of the State Key Lab of CADAMP
- CG, Zhejiang University [A1702]
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据