EditThinker: 解锁任何图像编辑器的迭代推理
EditThinker: Unlocking Iterative Reasoning for Any Image Editor
AI总结：
EditThinker通过迭代推理框架提升图像编辑指令遵循能力，利用强化学习优化编辑过程，显著提高模型性能。
摘要：
基于指令的图像编辑已成为一个重要的研究领域，得益于图像生成基础模型，已经实现了高质量的审美效果，但遵循指令的能力成为主要挑战。现有方法通过监督学习或强化学习提高指令遵循性，但单轮成功率仍受限于内在的随机性和缺乏深思熟虑。在本工作中，我们提出了一种反思编辑框架，使编辑过程中能够'思考'，通过迭代执行'思考-编辑'循环：批判结果并细化指令，然后重复生成直到满意。具体而言，我们训练了一个单一的MLLM，即EditThinker，作为该框架的推理引擎，共同生成批判评分、推理过程和细化指令。我们采用强化学习使EditThinker的思考与其编辑对齐，从而生成更针对性的指令改进。在四个基准上的大量实验表明，我们的方法显著提高了任何图像编辑模型的指令遵循能力。我们将发布我们的数据构建框架、数据集和模型，以造福社区。
英文摘要：
Instruction-based image editing has emerged as a prominent research area, which, benefiting from image generation foundation models, have achieved high aesthetic quality, making instruction-following capability the primary challenge. Existing approaches improve instruction adherence via supervised or reinforcement learning, yet single-turn success rates remain limited due to inherent stochasticity and a lack of deliberation. In this work, we propose a deliberative editing framework to 'think' while they edit, which simulates the human cognitive loop by iteratively executing a Think-while-Edit cycle: Critiquing results and Refining instructions , followed by Repeating the generation until satisfactory. Specifically, we train a single MLLM, EditThinker, to act as the reasoning engine of this framework, which jointly produce the critique score, reasoning process, and refined instructions. We employ reinforcement learning to align the EditThinker's thinking with its editing, thereby generating more targeted instruction improvements. Extensive experiments on four benchmarks demonstrate that our approach significantly improves the instruction-following capability of any image editing model by a large margin. We will release our data construction framework, datasets, and models to benefit the community.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
