TY - JOUR AU - Huang, Zhengyue AU - Zhao, Zhehui AU - Zhou, Hengguang AU - Zhao, Xibin AU - Gao, Yue PY - 2019/07/17 Y2 - 2024/03/28 TI - DeepCCFV: Camera Constraint-Free Multi-View Convolutional Neural Network for 3D Object Retrieval JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 33 IS - 01 SE - AAAI Technical Track: Vision DO - 10.1609/aaai.v33i01.33018505 UR - https://ojs.aaai.org/index.php/AAAI/article/view/4868 SP - 8505-8512 AB - <p>3D object retrieval has a compelling demand in the field of computer vision with the rapid development of 3D vision technology and increasing applications of 3D objects. 3D objects can be described in different ways such as voxel, point cloud, and multi-view. Among them, multi-view based approaches proposed in recent years show promising results. Most of them require a fixed predefined camera position setting which provides a complete and uniform sampling of views for objects in the training stage. However, this causes heavy over-fitting problems which make the models failed to generalize well in free camera setting applications, particularly when insufficient views are provided. Experiments show the performance drastically drops when the number of views reduces, hindering these methods from practical applications. In this paper, we investigate the over-fitting issue and remove the constraint of the camera setting. First, two basic feature augmentation strategies <em>Dropout</em> and <em>Dropview</em> are introduced to solve the over-fitting issue, and a more precise and more efficient method named <em>DropMax</em> is proposed after analyzing the drawback of the basic ones. Then, by reducing the over-fitting issue, a camera constraint-free multi-view convolutional neural network named <em>DeepCCFV</em> is constructed. Extensive experiments on both single-modal and cross-modal cases demonstrate the effectiveness of the proposed method in free camera settings comparing with existing state-of-theart 3D object retrieval methods.</p> ER -