AdaPilot：面向跨生成器文生图质量优化的场景自适应策略学习
AdaPilot: Towards Scene-Adaptive Policy Learning for Cross-Generator Text-to-Image Quality Optimization
- Nanyang Technological University（南洋理工大学）
- Hithink Research（海天瑞声研究院）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
AdaPilot通过将多轮图像生成建模为马尔可夫决策过程并采用端到端强化学习，学习场景自适应、跨生成器可迁移的质量优化策略，在生成质量和泛化性上超越基线。
中文摘要 AI 辅助
现有提升文生图质量的方法已从生成器微调和提示优化发展到利用多轮视觉反馈的强化学习。然而，现有策略与特定生成器和任务深度耦合，所学能力难以泛化为通用的质量优化策略。为此，我们提出AdaPilot，通过将多轮图像生成建模为马尔可夫决策过程（MDP），并采用端到端强化学习进行优化，学习一种场景自适应、跨生成器可迁移的质量优化策略。具体而言，AdaPilot将策略与生成器内部解耦以实现跨生成器迁移，引入场景感知奖励以自适应地将质量评估维度与任务语义对齐，并采用过程级奖励来建模图像质量的演化轨迹。实验结果表明，AdaPilot在生成质量和泛化性上优于基线方法。单独的跨生成器评估进一步表明，单一策略可零样本迁移至未见过的生成器，并在所有评估生成器上保持正向平均增益。我们的项目可在该网址获取。
英文摘要
Existing methods for improving text-to-image generation quality have progressed from generator fine-tuning and prompt optimization to reinforcement learning with multi-turn visual feedback. However, existing strategies are deeply coupled with specific generators and tasks, and the learned capabilities are difficult to generalize into a universal quality optimization policy. Therefore, we propose AdaPilot, which learns a scene-adaptive, cross-generator transferable quality optimization policy by formulating multi-turn image generation as a Markov Decision Process (MDP) and optimizing it via end-to-end reinforcement learning. Specifically, AdaPilot decouples the policy from generator internals to enable cross-generator transfer, introduces scene-aware rewards that adaptively align quality assessment dimensions with task semantics, and employs process-level rewards to model the evolution trajectory of image quality. Experimental results show AdaPilot outperforms baselines in generation quality and generalization. Separate cross-generator evaluations further show that a single policy transfers zero-shot to unseen generators while maintaining positive average gains across all evaluated generators. Our project is available at https://github.com/QwenQing/Ada_pilot.
