arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.05068cs.CVcs.AI
收藏

基于形状先验知识的单视图三维完成与重建

Learning Shape Priors for Single-View 3D Completion and Reconstruction

MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);Google Research(谷歌研究院)

Jiajun Wu, Chengkai Zhang, Xiuming Zhang, Zhoutong Zhang, William T. Freeman, Joshua B. Tenenbaum

摘要:

单视图3D形状完成或重建的问题是具有挑战性的,因为在解释观察的许多可能的形状中,大多数是难以置信的,并且不对应于自然对象。该领域最近的研究通过利用深度卷积网络的表现力来解决这个问题。事实上,还有另一个经常被忽视的模糊性:在看似合理的形状中,仍然有多个形状同样适合2D图像;即,在给定单视图输入的情况下,地面实况形状是不确定的。现有的完全监督方法无法解决这个问题,并且通常会产生具有平滑表面但没有精细细节的模糊平均形状。在本文中,我们提出了ShapeHD,通过将深度生成模型与逆向学习的形状先验知识相结合,推动了单视图形状完成和重建的极限。学习的先验作为正则化器,只有当模型的输出是不现实的时才惩罚模型,而不是如果它偏离了基本事实。因此,我们的设计克服了上述两个层次的模糊性。实验表明,ShapeHD在多个真实数据集上的形状完成和形状重建方面都大大优于现有技术。

英文摘要:

The problem of single-view 3D shape completion or reconstruction is challenging, because among the many possible shapes that explain an observation, most are implausible and do not correspond to natural objects. Recent research in the field has tackled this problem by exploiting the expressiveness of deep convolutional networks. In fact, there is another level of ambiguity that is often overlooked: among plausible shapes, there are still multiple shapes that fit the 2D image equally well; i.e., the ground truth shape is non-deterministic given a single-view input. Existing fully supervised approaches fail to address this issue, and often produce blurry mean shapes with smooth surfaces but no fine details. In this paper, we propose ShapeHD, pushing the limit of single-view shape completion and reconstruction by integrating deep generative models with adversarially learned shape priors. The learned priors serve as a regularizer, penalizing the model only if its output is unrealistic, not if it deviates from the ground truth. Our design thus overcomes both levels of ambiguity aforementioned. Experiments demonstrate that ShapeHD outperforms state of the art by a large margin in both shape completion and shape reconstruction on multiple real datasets.

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。

↑