RePlan：基于推理的复杂基于指令的图像编辑区域规划
RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing
AI总结：
研究针对复杂指令图像编辑中现有模型在IV-复杂性下的不足，提出RePlan框架，结合视觉语言规划器与扩散编辑器，经强化学习提升性能，还推出IV-Edit基准，该框架在相关设置中优于强大基线，提高了区域精度和整体一致性。
摘要：
基于指令的图像编辑能够通过自然语言控制视觉修改，但现有模型在指令-视觉复杂性（IV-复杂性）下表现不佳，即复杂指令遇到杂乱或模糊场景时。我们引入了RePlan（区域对齐规划），这是一个先规划后执行的框架，将视觉语言规划器与扩散编辑器相结合。规划器通过逐步推理分解指令并将其明确锚定到目标区域；编辑器然后使用无训练注意力区域注入机制应用更改，实现精确的并行多区域编辑而无需迭代修复。为加强规划，我们使用1000个仅含指令的示例应用基于GRPO的强化学习，在推理保真度和格式可靠性方面取得显著提升。我们还提出了IV-Edit，一个专注于细粒度锚定和知识密集型编辑的基准。在IV-复杂设置中，RePlan始终优于在大得多的数据集上训练的强大基线，提高了区域精度和整体一致性。
英文摘要：
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
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。
