PosterReward: Unlocking Accurate Evaluation for High-Quality Graphic Design Generation

TL;DR

PosterReward introduces a specialized reward model for accurate poster design evaluation, leveraging a large dataset of simulated preferences and a multi-stage training process to improve assessment of typography and layout.

Contribution

The paper presents a novel dataset and a reward model tailored for high-quality poster evaluation, addressing limitations of existing models and enhancing graphic design generation.

Findings

PosterReward outperforms existing reward models in poster assessment.

The dataset of 70k poster preferences enables more accurate evaluation.

Benchmark results show improved poster generation quality.

Abstract

Recent advancements in the text-rendering capabilities of image generation models have made the end-to-end creation of graphic design content, such as posters, increasingly feasible. However, existing reward models fall short of accurately assessing design quality, as they primarily focus on global image aesthetics while overlooking the critical dimensions of typography and layout. Furthermore, the scarcity of domain-specific preference data remains a significant bottleneck, which limits the further development of graphic design evaluation and generation. To bridge this gap, we introduce an automated pipeline to construct a high-quality dataset of 70k poster preferences by leveraging the consensus of multiple Multi-modal Large Language Models (MLLMs) to simulate human-like judgment. Utilizing this dataset, we develop PosterReward, a reward model specifically designed for high-precision poster assessment through a cascaded, multi-stage training strategy. We also provide multiple variants of the model to cater to different application scenarios. Finally, we introduce PosterRewardBench and PosterBench to evaluate the performance of existing reward models in poster assessment and the generation capabilities of current text-to-image models in poster creation, respectively.