Guided Focal Stack Refinement Network for Light Field Salient Object Detection

TL;DR

This paper introduces GFRNet, a novel network that refines focal stacks using multi-modal features to improve light field salient object detection accuracy, outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a guided focal stack refinement network with specialized modules for different modalities, enhancing structural information and SOD performance.

Findings

GFRNet outperforms 12 state-of-the-art models on four benchmark datasets.

The proposed modules effectively refine focal stacks and improve salient object detection.

Experimental results demonstrate the superiority of the method in accuracy and robustness.

Abstract

Light field salient object detection (SOD) is an emerging research direction attributed to the richness of light field data. However, most existing methods lack effective handling of focal stacks, therefore making the latter involved in a lot of interfering information and degrade the performance of SOD. To address this limitation, we propose to utilize multi-modal features to refine focal stacks in a guided manner, resulting in a novel guided focal stack refinement network called GFRNet. To this end, we propose a guided refinement and fusion module (GRFM) to refine focal stacks and aggregate multi-modal features. In GRFM, all-in-focus (AiF) and depth modalities are utilized to refine focal stacks separately, leading to two novel sub-modules for different modalities, namely AiF-based refinement module (ARM) and depth-based refinement module (DRM). Such refinement modules enhance structural and positional information of salient objects in focal stacks, and are able to improve SOD accuracy. Experimental results on four benchmark datasets demonstrate the superiority of our GFRNet model against 12 state-of-the-art models.