Light field salient object detection: A review and benchmark

52Citations
Citations of this article
45Readers
Mendeley users who have this article in their library.

This article is free to access.

Abstract

Salient object detection (SOD) is a long-standing research topic in computer vision with increasing interest in the past decade. Since light fields record comprehensive information of natural scenes that benefit SOD in a number of ways, using light field inputs to improve saliency detection over conventional RGB inputs is an emerging trend. This paper provides the first comprehensive review and a benchmark for light field SOD, which has long been lacking in the saliency community. Firstly, we introduce light fields, including theory and data forms, and then review existing studies on light field SOD, covering ten traditional models, seven deep learning-based models, a comparative study, and a brief review. Existing datasets for light field SOD are also summarized. Secondly, we benchmark nine representative light field SOD models together with several cutting-edge RGB-D SOD models on four widely used light field datasets, providing insightful discussions and analyses, including a comparison between light field SOD and RGB-D SOD models. Due to the inconsistency of current datasets, we further generate complete data and supplement focal stacks, depth maps, and multi-view images for them, making them consistent and uniform. Our supplemental data make a universal benchmark possible. Lastly, light field SOD is a specialised problem, because of its diverse data representations and high dependency on acquisition hardware, so it differs greatly from other saliency detection tasks. We provide nine observations on challenges and future directions, and outline several open issues. All the materials including models, datasets, benchmarking results, and supplemented light field datasets are publicly available at https://github.com/kerenfu/LFSOD-Survey. [Figure not available: see fulltext.].

References Powered by Scopus

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

15980Citations
N/AReaders
Get full text

Fully Convolutional Networks for Semantic Segmentation

8022Citations
N/AReaders
Get full text

Path Aggregation Network for Instance Segmentation

7113Citations
N/AReaders
Get full text

Cited by Powered by Scopus

CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection

92Citations
N/AReaders
Get full text

HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection

66Citations
N/AReaders
Get full text

Advances in deep concealed scene understanding

59Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Fu, K., Jiang, Y., Ji, G. P., Zhou, T., Zhao, Q., & Fan, D. P. (2022, December 1). Light field salient object detection: A review and benchmark. Computational Visual Media. Tsinghua University. https://doi.org/10.1007/s41095-021-0256-2

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 11

69%

Professor / Associate Prof. 3

19%

Researcher 2

13%

Readers' Discipline

Tooltip

Computer Science 12

75%

Engineering 3

19%

Nursing and Health Professions 1

6%

Article Metrics

Tooltip
Mentions
News Mentions: 1

Save time finding and organizing research with Mendeley

Sign up for free