Figure 1: We propose a new model for neural rendering of humans. The model is trained for a single person and can produce renderings of this person from novel viewpoints (top) or in the new body pose (bottom) unseen during training. To improve generalization, our model retains explicit texture representation, which is learned alongside the rendering neural network. AbstractWe present a system for learning full-body neural avatars, i.e. deep networks that produce full-body renderings of a person for varying body pose and camera position. Our system takes the middle path between the classical graphics pipeline and the recent deep learning approaches that generate images of humans using image-to-image translation. In particular, our system estimates an explicit twodimensional texture map of the model surface. At the same time, it abstains from explicit shape modeling in 3D. Instead, at test time, the system uses a fully-convolutional network to directly map the configuration of body feature points w.r.t. the camera to the 2D texture coordinates of individual pixels in the image frame. We show that such a system is capable of learning to generate realistic renderings while being trained on videos annotated with 3D poses and foreground masks. We also demonstrate that maintaining an explicit texture representation helps our system to achieve better generalization compared to systems that use direct image-to-image translation.

No abstract

The historical city is one of the most complex objects of research, being a “living” organism, the environment of modern man, a combination of natural and man-made, tangible and intangible elements. The relevance of the study of the historical and urban planning environment is caused by the ongoing search for the most effective approaches to preserving the heritage of cities and the sustainable development of their territories. Systematic and structural analysis of such a phenomenon as a historical city, identification of internal relationships of elements that make up the historical and urban planning environment; comparison of existing tools for the protection of urban planning heritage and determination of the most effective mechanism for its preservation, proposed by modern Russian legislation. Based on the analysis of existing tools for the protection of the historical urban planning environment, the authors propose to consider the procedure for determining the boundaries and subject of protection of historical settlements as one of the aspects of the implementation of the international approach to the preservation of historic urban landscapes (HUL approach), and identify ways to improve the national tools in the field of urban planning heritage protection.

No abstract

No abstract