Depth-Quality-Aware Salient Object Detection

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