PosterReward: Unlocking Accurate Evaluation for High-Quality Graphic Design Generation
This addresses the bottleneck in evaluating and generating high-quality posters for designers and AI developers, though it is incremental as it builds on existing reward modeling techniques.
The paper tackled the problem of inaccurate evaluation of graphic design quality in image generation models by introducing PosterReward, a reward model trained on a dataset of 70k poster preferences, which achieved high-precision assessment and was benchmarked against existing models.
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.