Style transfer is the process of rendering one image with some content in the style of another image, representing the style. Recent studies of Liu et al. (2017) show that traditional style transfer methods of Gatys et al. (2016) and Johnson et al.(2016) fail to reproduce the depth of the content image, which is critical for human perception. They suggest to preserve the depth map by additional regularizer in the optimized loss function, forcing preservation of the depth map. However these traditional methods are either computationally inefficient or require training a separate neural network for each style. AdaIN method of Huang et al. (2017) allows efficient transferring of arbitrary style without training a separate model but is not able to reproduce the depth map of the content image. We propose an extension to this method, allowing depth map preservation by applying variable stylization strength. Qualitative analysis and results of user evaluation study indicate that the proposed method provides better stylizations, compared to the original AdaIN style transfer method.
Style transfer is a problem of rendering image with some content in the style of another image, for example a family photo in the style of a painting of some famous artist. The drawback of classical style transfer algorithm is that it imposes style uniformly on all parts of the content image, which perturbs central objects on the content image, such as faces or text, and makes them unrecognizable. This work proposes a novel style transfer algorithm which automatically detects central objects on the content image, generates spatial importance mask and imposes style non-uniformly: central objects are stylized less to preserve their recognizability and other parts of the image are stylized as usual to preserve the style. Three methods of automatic central object detection are proposed and evaluated qualitatively and via a user evaluation study. Both comparisons demonstrate higher quality of stylization compared to the classical style transfer method.
Style transfer is a problem of rendering a content image in the style of another style image. A natural and common practical task in applications of style transfer is to adjust the strength of stylization. Algorithm of Gatys et al. [4] provides this ability by changing the weighting factors of content and style losses but is computationally inefficient. Real-time style transfer introduced by Johnson et al. [9] enables fast stylization of any image by passing it through a pre-trained transformer network. Although fast, this architecture is not able to continuously adjust style strength. We propose an extension to real-time style transfer that allows direct control of style strength at inference, still requiring only a single transformer network. We conduct qualitative and quantitative experiments that demonstrate that the proposed method is capable of smooth stylization strength control and removes Figure 1: Style transfer method proposed in this article omits artifacts generated by Johnson et al. [9] (a) and allows continuous control of stylization strength (b)-(d). 1 arXiv:1904.08643v1 [cs.CV] 18 Apr 2019 certain stylization artifacts appearing in the original real-time style transfer method. Comparisons with alternative real-time style transfer algorithms, capable of adjusting stylization strength, show that our method reproduces style with more details.
This article proposes a new forecast quality evaluation method for parametric models. The method takes into account the nonequivalence of forecast errors induced by different accuracies of evaluation of unknown parameters at different time instants and uses nonuniform weighting. Optimal weights values are determined and several numerical algorithms are proposed for their approximate evaluation. The method is tested using time series that describe real economic processes.
INTRODUCTIONOne of the most important problems of mathematical modeling is the choice of the best model describing observable data. In choosing such a model, qualitative and quantitative factors are usually taken into account. The model being considered must reflect qualitative characteristics of data, i.e., must describe the observable stationarity or nonstationarity of data, structural shifts in time or space, etc. However, in choosing some adequate model, in addition to qualitative characteristics, quantitative characteristics determining the exactness of describing the model by data are important. The problem arises of evaluation of the quality of forecasts for the model being considered. If the model is complicated but does not provide any gain in the exactness of forecasting observable data, then it makes sense to pass to the consideration of a simpler model with the same forecast accuracy. In the present article, a modification of the standard method of evaluating the quality of forecasts is considered.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.