让设计编辑既改得准又整体协调，还能保持结构完整。
SMART-Editor: A Multi-Agent Framework for Human-Like Design Editing with Structural Integrity
- 用奖励引导的推理与训练优化，保持全局一致性
- 在结构化场景中提升达15%，自然图像上也更优
- 适合需要高质量、连贯性设计修改的用户
我们提出SMART-Editor，一个用于结构化（海报、网页）和非结构化（自然图像）领域中组合式版面与内容编辑的多智能体框架。不同于以往仅做局部修改的模型，SMART-Editor通过两种策略保持全局连贯性：推理时的奖励引导精炼（Reward-Refine）和训练时的偏好优化（RewardDPO），后者使用对齐奖励的版面配对进行训练。为评估性能，我们构建SMARTEdit-Bench基准，涵盖多领域、级联编辑场景。实验显示，SMART-Editor优于InstructPix2Pix和HIVE等强基线，在结构化设置中RewardDPO最高提升15%，Reward-Refine在自然图像上表现更佳。自动与人工评估均证实，奖励引导规划能生成语义一致且视觉对齐的编辑结果。
原文摘要 · Abstract (English)
We present SMART-Editor, a framework for compositional layout and content editing across structured (posters, websites) and unstructured (natural images) domains. Unlike prior models that perform local edits, SMART-Editor preserves global coherence through two strategies: Reward-Refine, an inference-time rewardguided refinement method, and RewardDPO, a training-time preference optimization approach using reward-aligned layout pairs. To evaluate model performance, we introduce SMARTEdit-Bench, a benchmark covering multi-domain, cascading edit scenarios. SMART-Editor outperforms strong baselines like InstructPix2Pix and HIVE, with RewardDPO achieving up to 15% gains in structured settings and Reward-Refine showing advantages on natural images. Automatic and human evaluations confirm the value of reward-guided planning in producing semantically consistent and visually aligned edits.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。