ReContraster: Making Your Posters Stand Out with Regional Contrast

TL;DR

ReContraster is a training-free model that enhances poster design by leveraging regional contrast, using a multi-agent system and hybrid denoising to produce visually striking posters, validated by a new benchmark dataset.

Contribution

It introduces the first training-free regional contrast model for poster design, combining a multi-agent system and hybrid denoising, along with a new evaluation dataset.

Findings

ReContraster outperforms state-of-the-art methods in visual appeal.

Seven quantitative metrics and four user studies validate its effectiveness.

It produces posters that are both striking and aesthetically pleasing.

Abstract

Effective poster design requires rapidly capturing attention and clearly conveying messages. Inspired by the ``contrast effects'' principle, we propose ReContraster, the first training-free model to leverage regional contrast to make posters stand out. By emulating the cognitive behaviors of a poster designer, ReContraster introduces the compositional multi-agent system to identify elements, organize layout, and evaluate generated poster candidates. To further ensure harmonious transitions across region boundaries, ReContraster integrates the hybrid denoising strategy during the diffusion process. We additionally contribute a new benchmark dataset for comprehensive evaluation. Seven quantitative metrics and four user studies confirm its superiority over relevant state-of-the-art methods, producing visually striking and aesthetically appealing posters.