Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance

TL;DR

This paper introduces a novel dual graph learning framework with reciprocative guidance for light field saliency detection, effectively fusing focal stack features and all-focus images to improve accuracy.

Contribution

It proposes a dual graph model for focal stack feature fusion and a reciprocative guidance scheme for mutual feature enhancement, outperforming previous methods.

Findings

Achieves superior saliency detection accuracy over state-of-the-art methods.

Effectively models local context propagation with graph networks.

Demonstrates the benefit of mutual guidance between focal stack and all-focus features.

Abstract

The application of light field data in salient object de-tection is becoming increasingly popular recently. The diffi-culty lies in how to effectively fuse the features within the fo-cal stack and how to cooperate them with the feature of theall-focus image. Previous methods usually fuse focal stackfeatures via convolution or ConvLSTM, which are both lesseffective and ill-posed. In this paper, we model the infor-mation fusion within focal stack via graph networks. Theyintroduce powerful context propagation from neighbouringnodes and also avoid ill-posed implementations. On the onehand, we construct local graph connections thus avoidingprohibitive computational costs of traditional graph net-works. On the other hand, instead of processing the twokinds of data separately, we build a novel dual graph modelto guide the focal stack fusion process using all-focus pat-terns. To handle the second difficulty, previous methods usu-ally implement one-shot fusion for focal stack and all-focusfeatures, hence lacking a thorough exploration of their sup-plements. We introduce a reciprocative guidance schemeand enable mutual guidance between these two kinds of in-formation at multiple steps. As such, both kinds of featurescan be enhanced iteratively, finally benefiting the saliencyprediction. Extensive experimental results show that theproposed models are all beneficial and we achieve signif-icantly better results than state-of-the-art methods.