XCI-Sketch: Extraction of Color Information from Images for Generation of Colored Outlines and Sketches

TL;DR

This paper introduces two methods for generating colored sketches from images, one using image processing with color clustering and the other employing a GAN, to enhance sketch expressivity.

Contribution

It presents novel techniques combining image processing and deep learning to produce colored sketches from images, advancing sketch generation methods.

Findings

The image processing method effectively produces colored outlines.

The GAN-based approach generates realistic colored sketches from unseen images.

Quantitative and qualitative evaluations demonstrate the effectiveness of both methods.

Abstract

Sketches are a medium to convey a visual scene from an individual's creative perspective. The addition of color substantially enhances the overall expressivity of a sketch. This paper proposes two methods to mimic human-drawn colored sketches by utilizing the Contour Drawing Dataset. Our first approach renders colored outline sketches by applying image processing techniques aided by k-means color clustering. The second method uses a generative adversarial network to develop a model that can generate colored sketches from previously unobserved images. We assess the results obtained through quantitative and qualitative evaluations.