Bridging Unpaired Facial Photos And Sketches By Line-drawings

preprint2021arXivOpen access

Abstract

In this paper, we propose a novel method to learn face sketch synthesis models by using unpaired data. Our main idea is bridging the photo domain X\mathcal{X} and the sketch domain YY by using the line-drawing domain Z\mathcal{Z}. Specially, we map both photos and sketches to line-drawings by using a neural style transfer method, i.e. F:X/Y↦ZF: \mathcal{X}/\mathcal{Y} \mapsto \mathcal{Z}. Consequently, we obtain \textit{pseudo paired data} (Z,Y)(\mathcal{Z}, \mathcal{Y}), and can learn the mapping G:Z↦YG:\mathcal{Z} \mapsto \mathcal{Y} in a supervised learning manner. In the inference stage, given a facial photo, we can first transfer it to a line-drawing and then to a sketch by G∘FG \circ F. Additionally, we propose a novel stroke loss for generating different types of strokes. Our method, termed sRender, accords well with human artists' rendering process. Experimental results demonstrate that sRender can generate multi-style sketches, and significantly outperforms existing unpaired image-to-image translation methods.

Explore this paper’s authors, topics and related work.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Reviews 0

Write a reviewWrite

No reviews yet.

Discussion 0

Add a commentWrite

No comments yet.