Abstract As the Internet of Things continues to grow and thrive, more and more data are
consumed by machines for intelligent analysis. How to simultaneously support fast machine …

Example‐based methods are widely adopted in image super‐resolution (SR) to generate
clear, high‐resolution (HR) images from low‐resolution (LR) images. This paper reports our …

Mobile terminals have been accepted as main stream tools for online sociality, from which
people upload photos and videos to share their lives. However, the huge expense of …

Learning-based super-resolution has recently been proposed for enhancing human face
images, known as “face hallucination”. In this paper, we propose a novel algorithm to super …

Most popular learning-based super-resolution (SR) approaches suffer from complicated
learning structures and highly intensive computation, especially in resource-limited …

Due to the limits of bandwidth and storage space, digital images are usually down-scaled
and compressed when transmitted over networks, resulting in loss of details and jarring …

The existing face image super-resolution (FSR) algorithms usually train a specific model for
a specific low input resolution for optimal results. By contrast, we explore in this work a …

Existing approaches to learning-based face image super-resolution require low-resolution
testing inputs manually registered to pre-aligned highresolution training models [9, 12, 13 …

This paper presents an image compression method using deep learning based super-
resolution. Different from traditional image compression methods, we propose to select the …

Neural network-based image compressors have the ability to optimize various perceptual
image quality metrics. We propose improved methods that is based on selective-detail …