An Iterative Co-Saliency Framework for RGBD Images

TL;DR

This paper introduces an iterative RGBD co-saliency detection framework that refines common salient object maps by integrating depth information and employing a cycle of addition, deletion, and iteration schemes, improving detection consistency.

Contribution

It presents a novel iterative framework for RGBD co-saliency detection that incorporates depth cues and a refinement cycle, enhancing the accuracy over existing methods.

Findings

Effective exploitation of existing 2D saliency models in RGBD scenarios.

The proposed framework outperforms baseline methods on two RGBD datasets.

Introduction of a novel depth shape prior descriptor enhances co-saliency detection.

Abstract

As a newly emerging and significant topic in computer vision community, co-saliency detection aims at discovering the common salient objects in multiple related images. The existing methods often generate the co-saliency map through a direct forward pipeline which is based on the designed cues or initialization, but lack the refinement-cycle scheme. Moreover, they mainly focus on RGB image and ignore the depth information for RGBD images. In this paper, we propose an iterative RGBD co-saliency framework, which utilizes the existing single saliency maps as the initialization, and generates the final RGBD cosaliency map by using a refinement-cycle model. Three schemes are employed in the proposed RGBD co-saliency framework, which include the addition scheme, deletion scheme, and iteration scheme. The addition scheme is used to highlight the salient regions based on intra-image depth propagation and saliency propagation, while the deletion scheme filters the saliency regions and removes the non-common salient regions based on interimage constraint. The iteration scheme is proposed to obtain more homogeneous and consistent co-saliency map. Furthermore, a novel descriptor, named depth shape prior, is proposed in the addition scheme to introduce the depth information to enhance identification of co-salient objects. The proposed method can effectively exploit any existing 2D saliency model to work well in RGBD co-saliency scenarios. The experiments on two RGBD cosaliency datasets demonstrate the effectiveness of our proposed framework.