https://scholars.lib.ntu.edu.tw/handle/123456789/413042
標題: | Cross-domain image-based 3D shape retrieval by view sequence learning | 作者: | Lee T. Lin Y.-L. Chiang H. Chiu M.-W. Hsu W. POLLY HUANG |
關鍵字: | Image-based 3D shape retrieval; Triplet loss; View sequence learning | 公開日期: | 2018 | 起(迄)頁: | 258-266 | 來源出版物: | 2018 International Conference on 3D Vision, 3DV 2018 | 摘要: | We propose a cross-domain image-based 3D shape retrieval method, which learns a joint embedding space for natural images and 3D shapes in an end-to-end manner. The similarities between images and 3D shapes can be computed as the distances in this embedding space. To better encode a 3D shape, we propose a new feature aggregation method, Cross-View Convolution (CVC), which models a 3D shape as a sequence of rendered views. For bridging the gaps between images and 3D shapes, we propose a Cross-Domain Triplet Neural Network (CDTNN) that incorporates an adaptation layer to match the features from different domains better and can be trained end-to-end. In addition, we speed up the triplet training process by presenting a new fast cross-domain triplet neural network architecture. We evaluate our method on a new image to 3D shape dataset for category-level retrieval and ObjectNet3D for instance-level retrieval. Experimental results demonstrate that our method outperforms the state-of-the-art approaches in terms of retrieval performance. We also provide in-depth analysis of various design choices to further reduce the memory storage and computational cost. ? 2018 IEEE. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/413042 | ISBN: | 9781538684252 | DOI: | 10.1109/3DV.2018.00038 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。