arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.04157cs.CVcs.LG
收藏

预先了解深度质量:一种用于RGB-D显著目标检测的深度质量评估方法

Knowing Depth Quality In Advance: A Depth Quality Assessment Method For RGB-D Salient Object Detection

State Key Laboratory of VRTS, Beihang University(北京航空航天大学虚拟现实技术与系统国家重点实验室);College of Computer Science and Technology, Qingdao University(青岛大学计算机科学与技术学院);Stonybrook University(石溪大学)

Xuehao Wang, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin

摘要:

先前的RGB-D显着目标检测(SOD)方法已广泛采用深度学习工具来自动在RGB和D(深度)之间进行权衡,其关键原理是充分利用它们的互补性质,旨在比单独使用它们中的任何一个大大提高SOD性能。然而,这种全自动融合可能并不总是有助于SOD任务,因为D质量本身通常随场景而变化。如果不事先考虑D质量,则很容易导致次优融合结果。此外,作为一个客观因素,D质量长期被忽视的以前的工作。因此,它正在成为一个明显的性能瓶颈。因此,我们提出了一个简单而有效的计划来衡量D质量提前,其核心思想是设计一系列的功能,根据高质量的D区域的共同属性。更具体地说,我们进行D质量评估的每个图像区域,以下多尺度的方法,包括低级别的边缘一致性,中级区域的不确定性和高级别的模型方差。所有这些分量将被独立计算,然后与RGB和D特征组合,作为隐式指示器应用,以指导选择性融合。与现有的融合方法相比,该方法能够获得更合理的RGB与D的融合状态。具体而言,所提出的D质量测量方法实现了稳定的性能改善,一般接近2.0%。

英文摘要:

Previous RGB-D salient object detection (SOD) methods have widely adopted deep learning tools to automatically strike a trade-off between RGB and D (depth), whose key rationale is to take full advantage of their complementary nature, aiming for a much-improved SOD performance than that of using either of them solely. However, such fully automatic fusions may not always be helpful for the SOD task because the D quality itself usually varies from scene to scene. It may easily lead to a suboptimal fusion result if the D quality is not considered beforehand. Moreover, as an objective factor, the D quality has long been overlooked by previous work. As a result, it is becoming a clear performance bottleneck. Thus, we propose a simple yet effective scheme to measure D quality in advance, the key idea of which is to devise a series of features in accordance with the common attributes of high-quality D regions. To be more concrete, we conduct D quality assessments for each image region, following a multi-scale methodology that includes low-level edge consistency, mid-level regional uncertainty and high-level model variance. All these components will be computed independently and then be assembled with RGB and D features, applied as implicit indicators, to guide the selective fusion. Compared with the state-of-the-art fusion schemes, our method can achieve a more reasonable fusion status between RGB and D. Specifically, the proposed D quality measurement method achieves steady performance improvements for almost 2.0\% in general.

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。

↑