让复杂指令精准编辑图像多个区域，无需反复试错。
RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing
- 先拆解指令推理目标区域，再分步执行编辑
- 在1000个纯指令样本上强化训练，提升推理准确率
- 适合需要精细控制的图像编辑任务，如设计、修图
基于指令的图像编辑实现了自然语言对视觉修改的控制，但在指令与场景都复杂的场景下表现不佳。我们提出RePlan（区域对齐规划），一种先规划后执行的框架，由视觉语言规划器和扩散编辑器组成。规划器通过逐步推理将指令分解并显式定位到目标区域；编辑器则采用无训练的注意力-区域注入机制，实现无需迭代修复的并行多区域精确编辑。为增强规划能力，我们在1000个仅含指令的样本上使用GRPO强化学习，显著提升推理准确性和格式一致性。我们还构建了专注于细粒度定位与知识密集型编辑的IV-Edit基准。在复杂指令-视觉场景下，RePlan持续优于训练数据量大得多的强基线模型，在区域精度和整体一致性上均有提升。
原文摘要 · Abstract (English)
Instruction-based image editing enables natural-language control over visual modifications, yet existing models falter under Instruction-Visual Complexity (IV-Complexity), where intricate instructions meet cluttered or ambiguous scenes. We introduce RePlan (Region-aligned Planning), a plan-then-execute framework that couples a vision-language planner with a diffusion editor. The planner decomposes instructions via step-by-step reasoning and explicitly grounds them to target regions; the editor then applies changes using a training-free attention-region injection mechanism, enabling precise, parallel multi-region edits without iterative inpainting. To strengthen planning, we apply GRPO-based reinforcement learning using 1K instruction-only examples, yielding substantial gains in reasoning fidelity and format reliability. We further present IV-Edit, a benchmark focused on fine-grained grounding and knowledge-intensive edits. Across IV-Complex settings, RePlan consistently outperforms strong baselines trained on far larger datasets, improving regional precision and overall consistency. Our project page: https://replan-iv-edit.github.io
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。