论文标题
单眼深度和自我估计的自我监督量表恢复
Self-Supervised Scale Recovery for Monocular Depth and Egomotion Estimation
论文作者
论文摘要
对具有单眼图像的共同训练深度和自我训练深度和自我的神经网络的自我监督损失公式进行了充分的研究，并且已经证明了最先进的精度。但是，这种方法的主要局限性之一是，深度和自我估计仅确定为未知量表。在本文中，我们提出了一种新颖的规模恢复损失，该损失可在已知的摄像头高度和估计的摄像头高度之间执行一致性，从而产生度量（缩放）深度和自我预测。我们表明，我们提出的方法与需要更多信息的其他规模恢复技术具有竞争力。此外，我们证明我们的方法促进了在新环境中的网络重新培训，而其他规模分布的方法则无法做到。值得注意的是，与仅在测试时间恢复比例的类似方法相比，我们的eGomotion网络能够产生更准确的估计。
The self-supervised loss formulation for jointly training depth and egomotion neural networks with monocular images is well studied and has demonstrated state-of-the-art accuracy. One of the main limitations of this approach, however, is that the depth and egomotion estimates are only determined up to an unknown scale. In this paper, we present a novel scale recovery loss that enforces consistency between a known camera height and the estimated camera height, generating metric (scaled) depth and egomotion predictions. We show that our proposed method is competitive with other scale recovery techniques that require more information. Further, we demonstrate that our method facilitates network retraining within new environments, whereas other scale-resolving approaches are incapable of doing so. Notably, our egomotion network is able to produce more accurate estimates than a similar method which recovers scale at test time only.
