Time-of-Flight (ToF) cameras are subject to high levels of noise and distortions due to Multi-Path-Interference (MPI). While recent research showed that 2D neural networks are able to outperform previous traditional State-of-the-Art (SOTA) methods on denoising ToF-Data, little research on learning-based approaches has been done to make direct use of the 3D information present in depth images. In this paper, we propose an iterative denoising approach operating in 3D space, that is designed to learn on 2.5D data by enabling 3D point convolutions to correct the points' positions along the view direction. As labeled real world data is scarce for this task, we further train our network with a self-training approach on unlabeled real world data to account for real world statistics. We demonstrate that our method is able to outperform SOTA methods on several datasets, including two real world datasets and a new large-scale synthetic data set introduced in this paper.
翻译:由于多帕干涉(MPI),光线照相机受到高度噪音和扭曲的影响。虽然最近的研究表明,2D神经网络能够超越以往传统的艺术状态(SOTA)方法的去掉 ToF-Data,但对基于学习的方法的研究很少,无法直接利用深度图像中的3D信息。在本文件中,我们提议在3D空间操作一种迭代分解方法,目的是通过使3D点组合能够纠正沿观察方向的点位置来学习2.5D数据。由于这个任务上贴有标签的真实世界数据稀缺,我们进一步培训我们的网络,采用自我培训的方法,对不贴标签的真实世界数据进行核算,以记录真实世界统计数据。我们证明,我们的方法能够超越SOTA方法在若干数据集上的应用,包括两个真实的世界数据集和本文中介绍的新的大规模合成数据。