No abstract

Most of previous image denoising methods focus on additive white Gaussian noise (AWGN). However,the real-world noisy image denoising problem with the advancing of the computer vision techiniques. In order to promote the study on this problem while implementing the concurrent real-world image denoising datasets, we construct a new benchmark dataset which contains comprehensive real-world noisy images of different natural scenes. These images are captured by different cameras under different camera settings. We evaluate the different denoising methods on our new dataset as well as previous datasets. Extensive experimental results demonstrate that the recently proposed methods designed specifically for realistic noise removal based on sparse or low rank theories achieve better denoising performance and are more robust than other competing methods, and the newly proposed dataset is more challenging. The constructed dataset of real photographs is publicly available at https://github.com/csjunxu/PolyUDataset for researchers to investigate new real-world image denoising methods. We will add more analysis on the noise statistics in the real photographs of our new dataset in the next version of this article.

No abstract

No abstract

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. The illumination is obtained by iteratively solving a nonlinear diffusion equation. During the diffusion process, surround suppression is embedded in the conductance function to specially enhance the diffusive strength in textural areas of the image. The proposed estimation method has the following two merits: 1) the boundary areas are preserved in the illumination, and thus halo artifacts are prevented and 2) the textural details are preserved in the reflectance to not suffer from illumination compression, which contributes to the contrast enhancement in the result. Experimental results show that the proposed algorithm achieves excellent performance in artifact removal and local contrast enhancement.