Deep Learning Representation using Autoencoder for 3D Shape Retrieval

详细信息    查看全文

• 作者：Zhuotun Zhu ^{zhuotun@gmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Xinggang Wang ; ^{xgwang@hust.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Song Bai ^{songbai@hust.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Cong Yao ^{yaocong2010@gmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Xiang Bai ^{xbai@hust.edu.cn" class="auth_mail" title="E-mail the corresponding author}Author Vitae
• 关键词：3D Shape Matching ; 3D Shape Retrieval ; Autoencoder ; Shape Representation
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：5 September 2016
• 年：2016
• 卷：204
• 期：Complete
• 页码：41-50
• 全文大小：1792 K

文摘

We study the problem of how to build a deep learning representation for 3D shape. Deep learning has shown to be very effective in variety of visual applications, such as image classification and object detection. However, it has not been successfully applied to 3D shape recognition. This is because 3D shape has complex structure in 3D space and there are limited number of 3D shapes for feature learning. To address these problems, we project 3D shapes into 2D space and use autoencoder for feature learning on the 2D images. High accuracy 3D shape retrieval performance is obtained by aggregating the features learned on 2D images. In addition, we show the proposed deep learning feature is complementary to conventional local image descriptors. By combing the global deep learning representation and the local descriptor representation, our method can obtain the state-of-the-art performance on 3D shape retrieval benchmarks.