We propose automatic contrast-limited adaptive histogram equalization (CLAHE) for image contrast enhancement. We automatically set the clip point for CLAHE based on textureness of a block. Also, we introduce dual gamma correction into CLAHE to achieve contrast enhancement while preserving naturalness. First, we redistribute the histogram of the block in CLAHE based on the dynamic range of each block. Second, we perform dual gamma correction to enhance the luminance, especially in dark regions while reducing over-enhancement artifacts. Since automatic CLAHE adaptively enhances contrast in each block while boosting luminance, it is very effective in enhancing dark images and daylight ones with strong dark shadows. Moreover, automatic CLAHE is computationally efficient, i.e., more than 35 frames/s at 1024 × 682 resolution, due to the independent block processing for contrast enhancement. Experimental results demonstrate that automatic CLAHE with dual gamma correction achieves good performance in contrast enhancement and outperforms state-of-the-art methods in terms of visual quality and quantitative measures.

Gradient-boosted decision trees (GBDTs) are widely used in machine learning, and the output of current GBDT implementations is a single variable. When there are multiple outputs, GBDT constructs multiple trees corresponding to the output variables. The correlations between variables are ignored by such a strategy causing redundancy of the learned tree structures. In this article, we propose a general method to learn GBDT for multiple outputs, called GBDT-MO. Each leaf of GBDT-MO constructs predictions of all variables or a subset of automatically selected variables. This is achieved by considering the summation of objective gains over all output variables. Moreover, we extend histogram approximation into the multiple-output case to speed up training. Various experiments on synthetic and real data sets verify that GBDT-MO achieves outstanding performance in terms of accuracy, training speed, and inference speed.

Dilated convolutions support expanding receptive field without parameter exploration or resolution loss, which turn out to be suitable for pixel-level prediction problems. In this paper, we propose multiscale single image super-resolution based on dilated convolutions (DCSR). We adopt dilated convolutions to expand the receptive field size without incurring additional computational complexity. We mix standard convolutions and dilated convolutions in each layer, called mixed convolutions, i.e. in the mixed convolutional layer, the feature extracted by dilated convolutions and standard convolutions are concatenated. We theoretically analyze the receptive field and intensity of mixed convolutions to discover their role in SR. Mixed convolutions remove blind spots and capture the correlation between lowresolution (LR) and high-resolution (HR) image pairs successfully, thus achieving good generalization ability. We verify those properties of mixed convolutions by training 5-layer and 10-layer networks. We also train a 20-layer deep network to compare the performance of the proposed method with those of the state-ofthe- art ones. Moreover, we jointly learn maps with different scales from a low-resolution image to its high-resolution one in a single network. Experimental results demonstrate that the proposed method outperforms the state-of-the-art ones in terms of PSNR and SSIM, especially for a large scale factor.

In this paper, we propose retinex-based perceptual contrast enhancement in images using luminance adaptation. Strong illumination causes the loss of local details in an image. We adopt luminance adaptation and multi-scale retinex (MSR) to successfully remove the illumination effect in an image while enhancing details. First, we estimate the illumination component in an image by adaptive smoothing, and get luminance justnoticeable- difference (JND) from it using luminance adaptation. Then, we calculate an illumination weakening factor from luminance JND and conduct MSR based on it to enhance details. Finally, we perform contrast enhancement using adaptive gamma correction with weighted distribution (AGCWD). Experimental results demonstrate that the proposed method successfully enhances details in an image while preventing over- and under-enhancement as well as outperforms state-of-the-arts in terms of various quantitative measurements.

When people take a picture through glass, the scene behind the glass is often interfered by specular reflection. Due to relatively easy implementation, most studies have tried to recover the transmitted scene from multiple images rather than single image. However, the use of multiple images is not practical for common users in real situations due to the critical shooting conditions. In this paper, we propose single image reflection removal using convolutional neural networks. We provide a ghosting model that causes reflection effects in captured images. First, we synthesize multiple reflection images from the input single one based on ghosting model and relative intensity. Then, we construct an end-to-end network that consists of encoder and decoder. To optimize the network parameters, we use a joint training strategy to learn the layer separation knowledge from the synthesized reflection images. For the loss function, we utilize both internal and external losses in optimization. Finally, we apply the proposed network to single image reflection removal. Compared with the previous work, the proposed method does not need handcrafted features and specular filters for reflection removal. Experimental results show that the proposed method successfully removes reflection from both synthetic and real images as well as achieves the highest scores in PSNR, SSIM and FSIM.