Depth Quality Aware Salient Object Detection

TL;DR

This paper introduces a depth quality aware subnet into RGB-D salient object detection models, enabling better fusion by assessing and mitigating the influence of low-quality depth data, thus improving detection performance.

Contribution

The novel depth quality aware subnet enhances RGB-D fusion by selectively weighting depth information based on quality, addressing a key limitation of existing bi-stream methods.

Findings

Improved fusion results in low-quality depth scenarios

Enhanced salient object detection accuracy

Reduced negative impact of poor depth data

Abstract

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.