For instance, Maximilien Luce used strong blues and yellows to shade objects (Figure 2) Henri Matisse often used deep reds and greens in his paintings. This is because a repeated use of some sets of colors will eventually make their paintings stand out. On the other hand, distinguished artists often prefer to use their favorite color combinations over the actual colors of the objects being painted. Although artists have their own choices of colors, basic rules are usually respected as they help ensuring that the paintings are perceived properly (e.g., a morning scene should be understood as in a morning time).
For instance, to color an object, one should use warm colors for illuminated regions and cold colors for shaded regions. It is commonly known that there are certain rules of using colors in fine art. This can be observed from paintings of the world-renowned painters such as Paul Cezanne, Vincent van Gogh, Pierre-Auguste Renoir. To confirm the performance of our model, we also conducted quantitative experiments on datasets of digitized paintings collected from the Internet and received favorable results.Ī key observation behinds our approach is that color palettes extracted from an art collection often conform to a certain aesthetic style, which can be revealed by their density distribution. To this end, we developed a divide-and-conquer sorting algorithm to rearrange the colors in the palettes in a coherent order, which allows meaningful interpolation between color palettes. It was, however, challenging to apply density estimation to palette data as palettes often come as unordered sets of colors, which make it difficult to use conventional metrics on them. Via density estimation, we carried out various predictions and interpolations on palettes, which led to promising applications such as photo-style exploration, real-time color suggestion, and enriched photo recolorization. As artists often use their personal color themes in their paintings, making these palettes appear frequently in the dataset, we employed density estimation to capture the characteristics of palette data. We aim to capture color styles embedded in these collections by means of statistical models and to build practical applications upon these models. Although color palettes may come from different sources such as online crowd-sourcing, photographs and graphical designs, in this paper, we consider color palettes extracted from fine art collections, which we believe to be an abundant source of stylistic and unique color themes. Color theme or color palette can deeply influence the quality and the feeling of a photograph or a graphical design.
0 kommentar(er)
