Multi-Density Sketch-to-Image Translation Network

TL;DR

This paper introduces a novel multi-density sketch-to-image translation framework that enables flexible control over sketch details, from rough outlines to micro structures, improving image synthesis and manipulation tasks.

Contribution

It presents the first multi-level density S2I translation method with a continuous latent space for density control, enhancing flexibility and user control in image generation.

Findings

Effective across diverse datasets and applications.

Enables fine-grained control over sketch density.

Improves flexibility in sketch-to-image translation.

Abstract

Sketch-to-image (S2I) translation plays an important role in image synthesis and manipulation tasks, such as photo editing and colorization. Some specific S2I translation including sketch-to-photo and sketch-to-painting can be used as powerful tools in the art design industry. However, previous methods only support S2I translation with a single level of density, which gives less flexibility to users for controlling the input sketches. In this work, we propose the first multi-level density sketch-to-image translation framework, which allows the input sketch to cover a wide range from rough object outlines to micro structures. Moreover, to tackle the problem of noncontinuous representation of multi-level density input sketches, we project the density level into a continuous latent space, which can then be linearly controlled by a parameter. This allows users to conveniently control the densities of input sketches and generation of images. Moreover, our method has been successfully verified on various datasets for different applications including face editing, multi-modal sketch-to-photo translation, and anime colorization, providing coarse-to-fine levels of controls to these applications.