首页|3D SOC-Net: Deep 3D reconstruction network based on self-organizing clustering mapping
3D SOC-Net: Deep 3D reconstruction network based on self-organizing clustering mapping
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Elsevier
Image-based 3D reconstruction from a single-view image is critical and fundamental in many areas and can be integrated into many applications to provide useful functions. However, there are several crucial difficulties and challenges in accomplishing this process. For example, the issues of self-occlusion and lack of object information in a different perspective of viewing. Thus, the quality of the generated 3D shape from a single-view image may not be satisfactory and robust, hence affecting its feasibility in further applications. Conventionally, the 3D reconstruction process requires multiple input images such that the context of the target object can be fully conveyed. In this paper, we propose a new and simple, yet powerful framework that improves the quality of the generated point cloud from a single-view image. Concretely, the significant representatives are first discovered and selected by adopting a network architecture that contains both encoder and decoder models. Finally, the resultant point clouds are obtained by extracting the mean shape using the methods of Chamfer Distance (CD), Earth Mover's Distance (EMD), and Self-Organizing Map (SOM). As a result, the proposed algorithm is capable to demonstrate its robustness and effectiveness when compared to state-of-the-art 3D reconstruction methods. The best mean loss exhibited is 4.45 when evaluated on 12 classes in the ShapeNetCoreV1 dataset. In addition, qualitative results are presented to further verify the reliability of the proposed method.
3D reconstructionSingle-view imageEncoderDecoderConvolutional neural networkPoint cloud
Y.S. Gan、Weihao Chen、Wei-Chuen Yau、Ziyun Zou、Sze-Teng Liong、Shih-Yuan Wang
展开 >
School of Architecture, Feng Chin University, Taichung 40724, Taiwan ROC
School of Computing and Data Science, Xiamen University Malaysia, 43900 Sepang, Selangor, Malaysia
Department of Electronic Engineering, Feng Chia University, Takhung 40724, Taiwan ROC
Graduate Institute of Architecture, National Yang Ming Chiao Tung University, Hsinchu Taiwan ROC
NETL
NSTL
Elsevier
