In recent decades, the practice of demonstrating various static and video images to users using digital, processor-controlled, most often self-luminous devices (computer monitors, smartphone and tablet screens, etc.) has spurred the development of various methods to improve the perception of such images by means of computerized image preprocessing. This also applies to methods of preprocessing images shown to users with various refractive anomalies of the eye(s) (e.g., myopia or astigmatism) in situations where they are not armed with glasses or other corrective devices. Over the past 20+ years, researchers have published dozens of papers on this task, referred to as the precompensation task. In our opinion, the time has come to reflect on the development of scientific thought in this direction and to highlight the most important milestones in realizing the problems on the way to achieving “ideal” precompensation and in approaches to their successful solution. This is the focus of the first part of this review. In the second part, we focus on the current state of research in the stated area, highlight the problems not solved so far, and try to catch the trends of further development of image precompensation methods, paying maximum attention to neural network approaches.
Image precompensation aimed at correcting refractive errors of the human eye seeks to transform a displayed image so that, after being blurred by the observer’s ocular optics, the image projection on the retina closely matches the original picture. The optimal precompensation varies for different refractive errors, so taking into account the specific refractive distortion introduced by a particular eye is called personalization. Existing personalized precompensation methods rely on deconvolution with built-in constraints or further tone mapping, which either produce artifacts or impose contrast loss. In this paper, we propose an approach for adapting modern two-input neural networks developed for non-blind image deconvolution to the problem of personalized image precompensation. The purpose of two inputs is the capability of independently feeding the neural-network model with the image to process and the personal characteristic function of the observer’s eye. Based on the proposed technique, three neural-network models (USRNet-PC, DWDN-PC, and KerUnc-PC) were developed, the adaptation of which was rather a unified approach than individual transformation of each architecture. These models were then comprehensively compared with other modern personalized precompensation methods on the basis of objective quality metrics, computational performance, and the results of simulation-based human studies. It has been shown that USRNet-PC provides the best subjective quality of perception and the shortest processing time on a GPU, while DWDN-PC demonstrates the highest computational efficiency on x86 and ARM CPUs. Thus, a new neural-network approach is proposed for solving the precompensation problem, which appeared to be superior in quality to previously known methods.