StyleBlit: Fast Example-Based Stylization with Local Guidance

TL;DR

StyleBlit is a fast, real-time style transfer algorithm that uses local guidance to produce high-quality stylized images efficiently without optimization, ideal for low-resource devices.

Contribution

It introduces a novel, optimization-free approach for example-based style transfer with local guidance, achieving real-time performance on a CPU.

Findings

Produces high-quality stylized images in real-time

Significantly faster than previous optimization-based methods

Effective for applications with limited computational resources

Abstract

We present StyleBlit---an efficient example-based style transfer algorithm that can deliver high-quality stylized renderings in real-time on a single-core CPU. Our technique is especially suitable for style transfer applications that use local guidance - descriptive guiding channels containing large spatial variations. Local guidance encourages transfer of content from the source exemplar to the target image in a semantically meaningful way. Typical local guidance includes, e.g., normal values, texture coordinates or a displacement field. Contrary to previous style transfer techniques, our approach does not involve any computationally expensive optimization. We demonstrate that when local guidance is used, optimization-based techniques converge to solutions that can be well approximated by simple pixel-level operations. Inspired by this observation, we designed an algorithm that produces results visually similar to, if not better than, the state-of-the-art, and is several orders of magnitude faster. Our approach is suitable for scenarios with low computational budget such as games and mobile applications.