# Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance

Source: [Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance](<https://www.sota2.com/research/paper/68fa6ae91e209131cea2afcd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:35:16.571Z

Authors: Nian Liu, Wangbo Zhao, Dingwen Zhang, Junwei Han, Ling Shao

Published: 2021-10-02T00:54:39.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Salient Object Detection on DUTLF S.Aperture](<https://www.sota2.com/research/sota/salient-object-detection-on-dutlf-s-aperture.md>): Salient Object Detection; DUTLF S.Aperture; MAE: 0.046.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2110.00698>)

[PDF](<https://arxiv.org/pdf/2110.00698.pdf>)