We present an approach to estimate the poses of human heads in natural scenes. The essential features for estimating the head pose are the positions of the prominent facial featur...
—This paper proposes a framework for single-image super-resolution. The underlying idea is to learn a map from input low-resolution images to target high-resolution images based ...
This paper describes a complete low-complexity imaging system based on a single MEMS scanning mirror and a single photodetector, together with customized image enhancement algorit...
Ganchi Zhang, Li Li, Vladimir Stankovic, Lina Stan...
Abstract. This paper proposes a regression-based method for singleimage super-resolution. Kernel ridge regression (KRR) is used to estimate the high-frequency details of the underl...
This paper presents a simple and e ective post-processing method for compressed images. This work focuses on the cyclic time-variance introduced by block-based and subband transfo...