Joint Denoising and Demosaicking With Green Channel Prior for Real-World Burst Images.

Denoising and demosaicking are essential yet correlated steps to reconstruct a full color image from the raw color filter array (CFA) data. By learning a deep convolutional neural network (CNN), significant progress has been achieved to perform denoising and demosaicking jointly. However, most existing CNN-based joint denoising and demosaicking (JDD) methods work on a single image while assuming additive white Gaussian noise, which limits their performance on real-world applications.

CameraNet: A Two-Stage Framework for Effective Camera ISP Learning.

Traditional image signal processing (ISP) pipeline consists of a set of cascaded image processing modules onboard a camera to reconstruct a high-quality sRGB image from the sensor raw data. Recently, some methods have been proposed to learn a convolutional neural network (CNN) to improve the performance of traditional ISP. However, in these works usually a CNN is directly trained to accomplish the ISP tasks without considering much the correlation among the different components in an ISP.

A Benchmark for Edge-Preserving Image Smoothing.

Edge-preserving image smoothing is an important step for many low-level vision problems. Though many algorithms have been proposed, there are several difficulties hindering its further development. First, most existing algorithms cannot perform well on a wide range of image contents using a single parameter setting.

Contrast Enhancement by Nonlinear Diffusion Filtering.

To enhance the visual quality of an image that is degraded by uneven light, an effective method is to estimate the illumination component and compress it. Some previous methods have either defects of halo artifacts or contrast loss in the enhanced image due to incorrect estimation. In this paper, we discuss this problem and propose a novel method to estimate the illumination.