Face Sketch Synthesis with Style Transfer using Pyramid Column Feature
This work addresses the problem of generating realistic face sketches from photos for applications in art, forensics, or entertainment, representing an incremental improvement over existing methods.
The paper tackles face sketch synthesis from photos by proposing a deep neural network framework that generates sketches in a cascaded manner, first outlining facial shapes and then adding textures and shadings using a style transfer approach with pyramid column features. It demonstrates that this method outperforms state-of-the-art techniques in quantitative and qualitative evaluations, with codes made available for reproducibility.
In this paper, we propose a novel framework based on deep neural networks for face sketch synthesis from a photo. Imitating the process of how artists draw sketches, our framework synthesizes face sketches in a cascaded manner. A content image is first generated that outlines the shape of the face and the key facial features. Textures and shadings are then added to enrich the details of the sketch. We utilize a fully convolutional neural network (FCNN) to create the content image, and propose a style transfer approach to introduce textures and shadings based on a newly proposed pyramid column feature. We demonstrate that our style transfer approach based on the pyramid column feature can not only preserve more sketch details than the common style transfer method, but also surpasses traditional patch based methods. Quantitative and qualitative evaluations suggest that our framework outperforms other state-of-the-arts methods, and can also generalize well to different test images. Codes are available at https://github.com/chaofengc/Face-Sketch