Salient object detection, which simulates human visual perception in locating the most
significant object (s) in a scene, has been widely applied to various computer vision tasks …

Detecting and segmenting salient objects from natural scenes, often referred to as salient
object detection, has attracted great interest in computer vision. While many models have …

Most recent methods for RGB (red–green–blue)-thermal salient object detection (SOD)
involve several floating-point operations and have numerous parameters, resulting in slow …

As one of the fundamental technologies for scene understanding, semantic segmentation
has been widely explored in the last few years. Light field cameras encode the geometric …

Light field (LF) depth estimation is a crucial basis for LF-related applications. Most existing
methods are based on the Lambertian assumption and cannot deal with non-Lambertian …

Data augmentation (DA) is an efficient strategy for improving the performance of deep neural
networks. Recent DA strategies have demonstrated utility in single image super-resolution …

Compared with current RGB or RGB-D saliency detection datasets, those for light field
saliency detection often suffer from many defects, eg, insufficient data amount and diversity …

Light field (LF) cameras can record scenes from multiple perspectives, and thus introduce
beneficial angular information for image super-resolution (SR). However, it is challenging to …

This paper proposes a novel efficient convolutional neural network (CNN) for light field (LF)
spatial super-resolution (SR). Due to the high dimensionality of LF data, it is important to …

Light field salient object detection (LF SOD) has recently received increasing attention.
However, most current works typically rely on an individual focal stack backbone for feature …