arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.04159cs.CVcs.LG
收藏

深度质量感知的显著目标检测

Depth Quality Aware Salient Object Detection

Qingdao University(青岛大学);Stony Brook University(石溪大学)

Chenglizhao Chen, Jipeng Wei, Chong Peng, Hong Qin

摘要:

现有的基于融合的RGB-D显著性目标检测方法通常采用双流结构来实现RGB和深度(D)之间的融合折衷。D质量通常因场景而异,而SOTA双流方法是深度质量未知的,这容易导致在实现RGB和D之间的互补融合状态时存在很大困难,从而导致在面对低质量D时融合效果不佳。因此,本文尝试将一种新的深度质量感知子网集成到经典的双流结构中,旨在进行选择性RGB-D融合之前评估深度质量。与SOTA双流方法相比,该方法的主要优点是能够在RGB-D融合过程中降低低质量、无贡献甚至负贡献的D区域的重要性,实现RGB和D之间的互补状态。

英文摘要:

The existing fusion based RGB-D salient object detection methods usually adopt the bi-stream structure to strike the fusion trade-off between RGB and depth (D). The D quality usually varies from scene to scene, while the SOTA bi-stream approaches are depth quality unaware, which easily result in substantial difficulties in achieving complementary fusion status between RGB and D, leading to poor fusion results in facing of low-quality D. Thus, this paper attempts to integrate a novel depth quality aware subnet into the classic bi-stream structure, aiming to assess the depth quality before conducting the selective RGB-D fusion. Compared with the SOTA bi-stream methods, the major highlight of our method is its ability to lessen the importance of those low-quality, no-contribution, or even negative-contribution D regions during the RGB-D fusion, achieving a much improved complementary status between RGB and D.

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。

↑