Depth Quality Aware Salient Object Detection
This work addresses a domain-specific issue in computer vision for RGB-D salient object detection, offering an incremental improvement by making fusion depth quality aware.
The paper tackles the problem of poor fusion results in RGB-D salient object detection when depth quality is low by integrating a depth quality aware subnet into the bi-stream structure, resulting in improved complementary fusion and performance gains over state-of-the-art methods.
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.