Abstract
Stereo matching and flow estimation are two essential tasks for scene understanding, spatially in 3D and temporally in motion. Existing approaches have been focused on the unsupervised setting due to the limited resource to obtain the large-scale ground truth data. To construct a self-learnable objective, co-related tasks are often linked together to form a joint framework. However, the prior work usually utilizes independent networks for each task, thus not allowing to learn shared feature representations across models. In this paper, we propose a single and principled network to jointly learn spatiotemporal correspondence for stereo matching and flow estimation, with a newly designed geometric connection as the unsupervised signal for temporally adjacent stereo pairs. We show that our method performs favorably against several state-of-the-art baselines for both unsupervised depth and flow estimation on the KITTI benchmark dataset.
Abstract (translated)
立体匹配和流量估计是场景理解的两个基本任务，分别是三维空间和运动时间。由于获取大规模地面真实数据的资源有限，现有的方法集中在无监督的环境中。为了构建一个自我学习的目标，共同相关的任务经常被联系在一起，形成一个联合的框架。然而，先前的工作通常为每个任务使用独立的网络，因此不允许学习跨模型的共享特征表示。本文提出了一个单一的、有原则的网络来共同学习立体匹配和流估计的时空对应关系，新设计的几何连接作为临时相邻立体对的无监督信号。我们表明，对于基蒂基准数据集上的无监督深度和流量估计，我们的方法在多个最先进的基线上都表现良好。
URL
https://arxiv.org/abs/1905.09265
