arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1708.07969cs.CVcs.AIcs.LGcs.RO
收藏

基于对抗学习的单景深三维物体重建

3D Object Reconstruction from a Single Depth View with Adversarial Learning

University of Oxford(牛津大学);University of Warwick(华威大学);Heriot-Watt University(赫瑞瓦特大学);Imperial College London(伦敦帝国理工学院)

Bo Yang, Hongkai Wen, Sen Wang, Ronald Clark, Andrew Markham, Niki Trigoni

摘要:

在本文中,我们提出了一种新的3D-RecGAN方法,该方法使用生成对抗网络从单个任意深度视图重建给定对象的完整3D结构。与通常需要相同对象或类标签的多个视图来恢复完整的3D几何形状的现有工作不同,所提出的3D-RecGAN仅将对象的深度视图的体素网格表示作为输入,并且能够通过填充被遮挡/缺失区域来生成完整的3D占用网格。其核心思想是结合自动编码器的生成能力和条件生成对抗网络(GAN)框架,在高维体素空间中推断对象的精确和细粒度的3D结构。在大型合成数据集上进行的大量实验表明,所提出的3D-RecGAN在单视图3D对象重建方面明显优于现有技术,并且能够重建看不见的对象类型。我们的代码和数据可在https://github.com/Yang7879/3D-RecGAN上获得。

英文摘要:

In this paper, we propose a novel 3D-RecGAN approach, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks. Unlike the existing work which typically requires multiple views of the same object or class labels to recover the full 3D geometry, the proposed 3D-RecGAN only takes the voxel grid representation of a depth view of the object as input, and is able to generate the complete 3D occupancy grid by filling in the occluded/missing regions. The key idea is to combine the generative capabilities of autoencoders and the conditional Generative Adversarial Networks (GAN) framework, to infer accurate and fine-grained 3D structures of objects in high-dimensional voxel space. Extensive experiments on large synthetic datasets show that the proposed 3D-RecGAN significantly outperforms the state of the art in single view 3D object reconstruction, and is able to reconstruct unseen types of objects. Our code and data are available at: https://github.com/Yang7879/3D-RecGAN.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑