DEGAN: Detail-Enhanced Generative Adversarial Network for Monocular Depth based 3D Reconstruction

Author:

Liu Caixia1ORCID,Chen Yali1ORCID,Zhu Minhong1ORCID,Hao Chenhui2ORCID,Li Haisheng1ORCID,Wang Xiaochuan1ORCID

Affiliation:

1. School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing Key Laboratory of Big Data Technology for Food Safety, China

2. Beijing Institute of Artificial Intelligence, Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing University of Technology, China

Abstract

Although deep networks based 3D reconstruction methods can recover the 3D geometry given few inputs, they may produce unfaithful reconstruction when predicting occluded parts of 3D objects. To address the issue, we propose Detail-Enhanced Generative Adversarial Network (DEGAN) which consists of Encoder-Decoder based Generator (EDGen) and Voxel-Point Embedding Network based Discriminator (VPDis) for 3D reconstruction from a monocular depth image of an object. Firstly, EDGen decodes the features from the 2.5D voxel grid representation of an input depth image, and generates the 3D occupancy grid under GAN losses and a sampling point loss. The sampling loss can improve the accuracy of predicted points with high uncertainty. VPDis helps reconstruct the details under voxel and point adversarial losses, respectively. Experimental results show that DEGAN not only outperforms several state-of-the-art methods on both public ModelNet and ShapeNet datasets, but also predicts more reliable occluded/missing parts of 3D objects.

Publisher

Association for Computing Machinery (ACM)

Reference78 articles.

1. object dense reconstruction from a single depth view;Yang Bo;IEEE Trans. Pattern Anal. Mach. Intell.,2019

2. reconstruction of human body shape from a single commodity depth camera;Zhao Tianhao;IEEE Trans. Multim.,2019

3. Video-based outdoor human reconstruction;Hao Zhu;TCSVT,2017

4. Michael Goesele, Noah Snavely, Brian Curless, Hugues Hoppe, and Steven M. Seitz. Multi-view stereo for community photo collections. In ICCV, volume 1, pages 1–8, 2007.

5. Yasutaka Furukawa and Jean Ponce. Carved visual hulls for image-based modeling. In ECCV, pages 564–577, 2006.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3