论文标题
深度边缘：分割和深度之间的明确约束
The Edge of Depth: Explicit Constraints between Segmentation and Depth
论文作者
论文摘要
在这项工作中，我们研究了两项常见的计算机视觉任务，自我监督的深度估计以及图像的语义分割的相互益处。例如，为了帮助无监督的单眼深度估计，已经隐含地探索了语义分割的约束，例如共享和转换特征。相比之下，我们建议通过迭代地监督网络朝着本地最佳解决方案进行分割和深度之间的边界一致性，并以贪婪的方式最小化边界的一致性。在某种程度上，这是由于我们的观察到，即甚至接受有限的地面真相训练的语义分割（Kitti的200张图像）可以提供比任何基于图像的深度估计的（单眼或立体声）更准确的边框。通过广泛的实验，我们提出的方法在Kitti中无监督的单眼深度估计方面提高了最新技术。
In this work we study the mutual benefits of two common computer vision tasks, self-supervised depth estimation and semantic segmentation from images. For example, to help unsupervised monocular depth estimation, constraints from semantic segmentation has been explored implicitly such as sharing and transforming features. In contrast, we propose to explicitly measure the border consistency between segmentation and depth and minimize it in a greedy manner by iteratively supervising the network towards a locally optimal solution. Partially this is motivated by our observation that semantic segmentation even trained with limited ground truth (200 images of KITTI) can offer more accurate border than that of any (monocular or stereo) image-based depth estimation. Through extensive experiments, our proposed approach advances the state of the art on unsupervised monocular depth estimation in the KITTI.
