Efficient Super-Resolution driven by saliency selectivity

Abstract

This paper presents a low-complexity saliency detector targeted towards efficient selective Super-Resolution (SR). As a result, an improved efficient ATtentive-SELective Perceptual (AT-SELP) framework is presented. The proposed AT-SELP scheme results in a reduced computational complexity for iterative SR algorithms without any perceptible loss in the desired enhanced image/video quality. A perceptually significant set of active pixels is selected for processing by the SR algorithm based on a local contrast sensitivity threshold model and the proposed low complexity saliency detector. Simulation results show that the proposed AT-SELP scheme results in a 15-40% reduction in computational complexity over an efficient Selective Perceptual (SELP) SR scheme without degradation in the visual quality.

Image super resolution using saliency-modulated context-aware sparse decomposition

“…This means similar images of the LR image can be gathered to train an adaptive dictionary. Moreover, inspired by the work in [5], we consider introducing the saliency property of images to further improve the adaptiveness of the dictionary. Saliency refers to elements of a visual scene that are likely to attract the attention of human observers [6].…”

Salient object detection with high‐level prior based on Bayesian fusion

“…Salient object detection plays an important role in many computer vision applications, including image and video segmentation [1], object recognition [2, 3], object class discovery [4], image retargeting [5], image quality assessment [6, 7], image super‐resolution [8], and Person re‐identification [9], to name a few. It has been a fundamental element in psychology, neuroscience, and computer science for a long time, which is used for predicting where people look at an image at the start, and recently has been extended to detect the most salient object from images/videos.…”