In this paper, we introduce a new dataset, named InstaOrder, that can be used to understand the spatial relationships of instances in a 3D space. The dataset consists of 2.9M annotations of geometric orderings for class-labeled instances in 101K natural scenes. The scenes were annotated by 3,659 crowd-workers regarding (1) occlusion order that identifies occluder/occludee and (2) depth order that describes ordinal relations that consider relative distance from the camera. The dataset provides joint annotation of two kinds of orderings for the same instances, and we discover that the occlusion order and depth order are complementary. We also introduce a geometric order prediction network called InstaOrderNet, which is superior to state-of-the-art approaches. Moreover, we propose InstaDepthNet that uses auxiliary geometric order loss to boost the instance-wise depth prediction accuracy of MiDaS. These contributions to geometric scene understanding will help to improve the accuracy of various computer vision tasks.

本文介绍了一个名为InstaOrder的新数据集，其中包括101K个自然场景中的2.9M个类别标注的实例几何排序注解，包括遮挡序和深度序；此外，还提出了一种名为InstaOrderNet的几何排序预测网络，以及一种名为InstaDepthNet的密集深度预测网络。

自然场景中的逐实例遮挡和深度排序