Abstract
Considering the significant progress made on RGB-based deep salient object detection (SOD) methods, this paper seeks to bridge the gap between those 2D methods and 4D light field data, instead of implementing specific 4D methods. We observe that the performance of 2D methods changes dramatically with the input refocusing on different depths. This paper attempts to make the 2D methods available for light field SOD by learning to select the best single image from the 4D tensor. Given a 2D method, a deep model is proposed to explicitly compare pairs of SOD results on one light field sample. Moreover, a comparator module is designed to integrate the features from a pair, which provides more discriminative representations to classify. Experiments over 13 latest 2D methods and 2 datasets demonstrate the proposed method can bring about 24.0% and 5.3% average improvement of mean absolute error and F-measure, and outperform state-of-the-art 4D methods by a large margin.
Highlights
Salient object detection (SOD), known as saliency detection, refers to simulate visual attention processes of human vision systems, which helps humans to quickly understand visual scenes and filter irrelevant information
5 Conclusions In this paper, we provide an alternative solution for the task of light field SOD
Without designing specialized segmentation network for light field data, a model is proposed to optimize the input of existing 2D methods, which have made significant progress
Summary
Salient object detection (SOD), known as saliency detection, refers to simulate visual attention processes of human vision systems, which helps humans to quickly understand visual scenes and filter irrelevant information. SOD aims to localize and segment the most visually attractive objects and ignore other region. Such technology has been regarded as a fundamental step for various computer vision problems, such as tracking [1], image fusion [2], detection [3], and segmentation [4, 5]. Existing SOD methods can be categorized into 2D, 3D, and 4D, which depends on the types of input, i.e., RGB, RGBD, and light field data, respectively. In the task of light field SOD, Liu et al EURASIP Journal on Image and Video Processing (2020) 2020:49
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
