arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.04467cs.CVcs.LG
收藏

基于深度网络的方向一致性单目深度估计

Monocular Depth Estimation with Directional Consistency by Deep Networks

University of Applied Sciences Munich(慕尼黑应用科学大学)

Fabian Truetsch, Alfred Schöttl

摘要:

随着处理能力变得越来越可用,越来越多的类人人工智能被创造出来,以解决我们天生擅长的图像处理任务。因此,我们提出了一个模型,估计从单目图像的深度。我们的方法利用了运动运动恢复结构和立体视差的组合。我们估计源图像与不同视点之间的姿态和密集深度图,并使用简单的变换来重建从所述视点看到的图像。然后,我们可以使用该视点处的真实图像作为监督来训练出模型。选择用于图像比较的度量采用标准L1和结构相似性以及深度图之间的一致性约束以及平滑度约束。我们发现,类似于人类的感知,利用两种不同方法提供的数据内的相关性,提高了准确性,并优于单个组件。

英文摘要:

As processing power has become more available, more human-like artificial intelligences are created to solve image processing tasks that we are inherently good at. As such we propose a model that estimates depth from a monocular image. Our approach utilizes a combination of structure from motion and stereo disparity. We estimate a pose between the source image and a different viewpoint and a dense depth map and use a simple transformation to reconstruct the image seen from said viewpoint. We can then use the real image at that viewpoint to act as supervision to train out model. The metric chosen for image comparison employs standard L1 and structural similarity and a consistency constraint between depth maps as well as smoothness constraint. We show that similar to human perception utilizing the correlation within the provided data by two different approaches increases the accuracy and outperforms the individual components.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑