Existing low-light image enhancement techniques are mostly not only difficult to deal with
both visual quality and computational efficiency but also commonly invalid in unknown …

Enhancing images in low-light scenes is a challenging but widely concerned task in the
computer vision. The mainstream learning-based methods mainly acquire the enhanced …

Most modern commodity imaging systems we use directly for photography—or indirectly rely
on for downstream applications—employ optical systems of multiple lenses that must …

This paper presents an approach for image cartoonization. By observing the cartoon
painting behavior and consulting artists, we propose to separately identify three white-box …

Imbalanced data cause deep neural networks to output biased results, and it becomes more
serious when facing extremely imbalanced data regarding the outliers with tiny size (the …

We propose a general dual convolutional neural network (DualCNN) for low-level vision
problems, eg, super-resolution, edge-preserving filtering, deraining, and dehazing. These …

Global structure and local detailed texture have different effects on image enhancement
tasks. However, most existing works treated these two components in the same way, without …

Image smoothing is a fundamental procedure in applications of both computer vision and
graphics. The required smoothing properties can be different or even contradictive among …

Hyperparameter Optimization in Black-box Image Processing using Differentiable Proxies
Page 1 Hyperparameter Optimization in Black-box Image Processing using Differentiable …

Convolutional neural networks (CNNs) designed for object recognition have been
successfully applied to low-level tasks such as image filtering. However, these networks are …