Artistic Enhancement and Style Transfer of Image Edges using Directional Pseudo-coloring
This work addresses the need for more visually appealing edge representations in computer vision, though it appears incremental as it builds on existing gradient techniques.
The paper tackles the problem of enhancing image edges by introducing directional pseudo-coloring to color the image gradient based on direction, improving visual quality and enabling artistic transformations. It also presents a style transfer pipeline that learns color maps from style images to apply to content images.
Computing the gradient of an image is a common step in computer vision pipelines. The image gradient quantifies the magnitude and direction of edges in an image and is used in creating features for downstream machine learning tasks. Typically, the image gradient is represented as a grayscale image. This paper introduces directional pseudo-coloring, an approach to color the image gradient in a deliberate and coherent manner. By pseudo-coloring the image gradient magnitude with the image gradient direction, we can enhance the visual quality of image edges and achieve an artistic transformation of the original image. Additionally, we present a simple style transfer pipeline which learns a color map from a style image and then applies that color map to color the edges of a content image through the directional pseudo-coloring technique. Code for the algorithms and experiments is available at https://github.com/shouvikmani/edge-colorizer.