Landscape Painterly Rendering Based on Observation

摘要

Painterly rendering is one of Non-Photorealisitic rendering skills that seems similar to paintings using 2D or 3D model data. We can notice from paintings that painters observe the scene in a short or long time when they draw. However, there are some limits in previous works using single image. They cannot emphasize attributes of objects such as motion. In this paper, we use observative information. For this, we first analyze motion, color, and position information from the inputted scene. From this information, we classify the objects. And then rendering depend on analyzed information. This skill has an advantage to simulate landscape paintings.