Genetic Paint: A Search for Salient Paintings
نویسندگان
چکیده
The contribution of this paper is a novel non-photorealistic rendering (NPR) algorithm for rendering real images in an impasto painterly style. We argue that figurative artworks are salience maps, and develop a novel painting algorithm that uses a genetic algorithm (GA) to search the space of possible paintings for a given image, so approaching an “optimal” artwork in which salient detail is conserved and non-salient detail is attenuated. We demonstrate the results of our technique on a wide range of images, illustrating both the improved control over level of detail due to our salience adaptive painting approach, and the benefits gained by subsequent relaxation of the painting using the GA.
منابع مشابه
Salience-adaptive Painterly Rendering Using Genetic Search
We present a new non-photorealistic rendering (NPR) algorithm for rendering photographs in an impasto painterly style. We observe that most existing image-based NPR algorithms operate in a spatially local manner, typically as non-linear image filters seeking to preserve edges and other high-frequency content. By contrast, we argue that figurative artworks are salience maps, and develop a novel ...
متن کاملLYOTARD’S DANCE of PAINT
I recently experienced a difficult creative block, which led me to switch my painting medium from acrylic to watercolor. For many years I had poured acrylic paint as part of a processoriented method of making paintings. That is to say, the use of the human hand was minimized, the paintings allowed to “grow” on their own. But I had become bored with this method and felt limited by my technique. ...
متن کاملStroke Matching for Paint Dances
We have implemented a non-photorealistic rendering system which simulates the placement of paint/pencil/pastel strokes to produce representational artworks from digital images. The system is able to record an image of each paint stroke independent of the overall picture, in addition to some details about each stroke. Working with sets of paint strokes from paintings of different images, we inve...
متن کاملModern Non-destructive Physical Methods for Paintings Testing and Evaluation
There are several rapidly developing non-destructive physical methods that are increasingly used for the analysis and assessment of art objects. These technologies are posed to bring about drastic changes in the attribution and inventory characterization procedures carried out by museums, private collections, art dealers, and art community as a whole. Certainly today nondestructive evaluation (...
متن کاملNanoindentation and the micromechanics of Van Gogh oil paints
Understanding the mechanical properties of ancient paintings is a major issue for conservation and restoration. One strategy is to measure the mechanical properties of reconstructed paints: however the aging process is poorly known, so it is also desirable to measure mechanical properties directly on ancient paint samples. Using nanoindentation, we have characterized submillimetric samples reco...
متن کامل