Creating Various Styles of Animations
Using Example-Based Filtering

Abstract

A number of Non-Photorealistic Rendering methods for producing artistic style images are proposed. Recently, a method called "Image Analogies" is proposed. This method is based on the notion of example-based filtering that uses a pair of images (an original image and a filtered image) as training data and generate an image which has a style that resembles the filtered image of the training data. This method has a great flexibility since the users can generate various styles of images by simply changing the training data. In this paper, we extend "Image Analogies" to generate various styles of animations. The coherence between frames is considered by computing the pixel flows between the frames. From experimental results, the proposed method can generate nice animation sequences.

Results

• Artistic style   (Oil paintings)
• Artistic style   (Watercolor paintings)
• Artistic style   (Pen-and-Ink styles)
• Texture-by-numbers   (Flowers)
• Various styles of animation   (Crosswalk)

Publications

• Ryota Hashimoto, Henry Johan, and Tomoyuki Nishita, "Creating Various Styles of Animations Using Example-Based Filtering", Computer Graphics International 2003, Tokyo (Japan), July 2003.  PDF (6.66MB)