PosterReward：为高质量平面设计生成解锁准确评估
PosterReward: Unlocking Accurate Evaluation for High-Quality Graphic Design Generation
为文生图模型提供针对海报设计的细粒度奖励信号，可用于生成后筛选或作为强化学习/偏好优化（如 RLHF、DPO）的奖励函数，弥补现有美学奖励模型忽略排版与文字准确性的缺陷。
原文依据 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
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期图像生成模型在文字渲染能力上的进展，使得海报等平面设计内容的端到端创作日益可行。然而，现有奖励模型难以准确评估设计质量，因为它们主要关注整体图像美学，而忽视了排版与布局这些关键维度。此外，领域特定偏好数据的稀缺仍是显著瓶颈，限制了平面设计评估与生成的进一步发展。为弥补这一空白，我们设计了一套自动化流程，借助多个多模态大语言模型（MLLM）的共识来模拟类人判断，从而构建了包含 7 万条海报偏好的高质量数据集。基于该数据集，我们提出 PosterReward，一种通过级联多阶段训练策略专门面向高精度海报评估而设计的奖励模型。我们还提供了该模型的多个变体，以适配不同应用场景。最后，我们引入 PosterRewardBench 与 PosterBench，分别用于评估现有奖励模型在海报评估上的表现，以及当前文生图模型在海报创作上的生成能力。
英文原文摘要 1280 字符
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, limiting the further development of graphic design evaluation and generation. To bridge this gap, we design 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. Based on this dataset, we propose 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.