Our paper addresses the complex task of transferring a hairstyle from a reference image to an input photo for virtual hair try-on. This task is challenging due to the need to adapt to various photo poses, the sensitivity of hairstyles, and the lack of objective metrics. The current state of the art hairstyle transfer methods use an optimization process for different parts of the approach, making them inexcusably slow. At the same time, faster encoder-based models are of very low quality because they either operate in StyleGAN's W+ space or use other low-dimensional image generators. Additionally, both approaches have a problem with hairstyle transfer when the source pose is very different from the target pose, because they either don't consider the pose at all or deal with it inefficiently. In our paper, we present the HairFast model, which uniquely solves these problems and achieves high resolution, near real-time performance, and superior reconstruction compared to optimization problem-based methods. Our solution includes a new architecture operating in the FS latent space of StyleGAN, an enhanced inpainting approach, and improved encoders for better alignment, color transfer, and a new encoder for post-processing. The effectiveness of our approach is demonstrated on realism metrics after random hairstyle transfer and reconstruction when the original hairstyle is transferred. In the most difficult scenario of transferring both shape and color of a hairstyle from different images, our method performs in less than a second on the Nvidia V100.

Hyper visors and virtual machines have become very popular in recent decade due to a number of indisputable advantages. But there is a dark side of this fact, especially for industry companies which are engaged into development of safety-relevant systems. The software becomes too complicated and bloated to meet all possible versions and configurations of hardware. As a result it's difficult to certify it with compliance to safety standards such as IEC 61508. An attempt to go another way is undertaken in the research. The way is to develop a bare-metal hyper visor for a particular platform with a certain set of peripheral devices and thus to reduce lines of code significantly. This approach allows making the software faster and more reliable in exchange for flexibility. The hardware-specific bare-metal microhypervisor has been developed from the scratch for x86 quad-core CPU. It can run three real-time virtual machines on separated cores. The main achievements are just not above 10k lines of code and simplicity.