.png){kind=icon}
返回
3D Patch-Based Sparse Learning for Style Feature Extraction
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2019.2954693.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
How to extract features of different shapes for style similarity evaluation is a very challenging research topic. Different from methods based on predefined style templates, we perform sparse learning and triplet embedding directly from the 3D shape local descriptors. The proposed method can adaptively generate element-level style features of different 3D patches for style similarity evaluation. The proposed algorithm mainly consists of the following steps. First, given a heterogeneous 3D shape collection, we learn mid-level style features by Siamese networks based on curvature-guided sampling directly on 3D shapes, which is a view-independent and part-independent approach. Second, we perform sparse coding to reduce the dimension of mid-level local features and achieve more compact and discriminative style features, named element-level features. Finally, we enhance our element-level style features by triplet embedding learning over crowdsourced triplets, which maps similar examples close to each other and dissimilar examples farther apart. The proposed algorithm can aggregate different local features into a global style feature representation and shows satisfactory discriminability. Our method can avoid the loss of style features from the 3D model to the views and can learn more discriminative style features by sparse learning. The experimental results show that our sparse style feature representation significantly improves the accuracy compared with recent state-of-the-art algorithms.
Keyword:
3D shape analysis
style feature
sparse learning
3D patch
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
.png){kind=icon}
Learning Local Shape Descriptors from Part Correspondences with Multiview Convolutional NetworksOAAI
OAAI分享收藏
分享收藏分享收藏
查看更多内容