Abstract
Single image depth estimation (SIDE) plays a crucial role in 3D computer vision. In this paper, we propose a two-stage robust SIDE framework that can perform blind SIDE for both indoor and outdoor scenes. At the first stage, the scene understanding module will categorize the RGB image into different depth-ranges. We introduce two different scene understanding modules based on scene classification and coarse depth estimation respectively. At the second stage, SIDE networks trained by the images of specific depth-range are applied to obtain an accurate depth map. In order to improve the accuracy, we further design a multi-task encoding-decoding SIDE network DS-SIDENet based on depthwise separable convolutions. DS-SIDENet is optimized to minimize both depth classification and depth regression losses. This improves the accuracy compared to a single-task SIDE network. Experimental results demonstrate that training DS-SIDENet on an individual dataset such as NYU achieves competitive performance to the state-of-art methods with much better efficiency. Ours proposed robust SIDE framework also shows good performance for the ScanNet indoor images and KITTI outdoor images simultaneously. It achieves the top performance compared to the Robust Vision Challenge (ROB) 2018 submissions.
Abstract (translated)
单幅图像深度估计在三维计算机视觉中起着至关重要的作用。在本文中,我们提出了一个两阶段的鲁棒侧框架,可以对室内和室外场景进行盲侧处理。在第一阶段,场景理解模块会将RGB图像分类为不同的深度范围。分别介绍了基于场景分类和粗深度估计的两种不同的场景理解模块。在第二阶段,应用由特定深度范围图像训练的边网,得到精确的深度图。为了提高译码精度,我们进一步设计了一种基于反方向可分卷积的多任务译码边网DS边网。对DS侧网进行了优化,使深度分类和深度回归损失最小化。与单个任务端网络相比,这提高了准确性。实验结果表明,在单个数据集(如纽约大学)上对DS Sidenet进行培训,可以获得与最新方法相比具有竞争力的性能,并且效率更高。我们提出的健壮的侧框架也显示了良好的性能,同时扫描室内图像和基蒂室外图像。与2018年Rob提交的强劲愿景挑战(Rob)相比,它实现了最高性能。
URL
https://arxiv.org/abs/1906.03279