生成式视觉链式思维用于图像编辑
Generative Visual Chain-of-Thought for Image Editing
AI总结：
本文提出GVCoT框架，通过生成空间线索实现视觉推理与编辑，解决复杂场景下的编辑定位问题，提出GVCoT-Edit-Instruct数据集和SREdit-Bench基准，实验表明其在图像编辑任务中表现优异。
摘要：
现有图像编辑方法在复杂场景和细微空间指令下难以定位编辑区域。为解决此问题，我们提出生成式视觉链式思维（GVCoT），一种统一框架，通过先生成空间线索定位目标区域再执行编辑。不同于以往纯文本链式思维或依赖工具的视觉链式思维范式，GVCoT在推理和编辑阶段以端到端方式联合优化视觉令牌。这促进了内在空间推理能力的产生，并更有效地利用视觉领域线索。GVCoT训练的主要挑战在于缺乏大规模具有精确编辑区域标注的编辑数据；为此，我们构建了包含19个任务的180万高质量样本的GVCoT-Edit-Instruct数据集。我们采用逐步训练策略：先通过监督微调建立推理轨迹的基础定位能力，再通过强化学习进一步提升推理和编辑质量。最后，我们引入SREdit-Bench，一个新基准，用于在复杂场景和细粒度指称表达下全面压力测试模型。实验表明，GVCoT在SREdit-Bench和ImgEdit任务上均优于现有最先进模型。我们希望GVCoT能启发未来向可解释和精确图像编辑方向的研究。
英文摘要：
Existing image editing methods struggle to perceive where to edit, especially under complex scenes and nuanced spatial instructions. To address this issue, we propose Generative Visual Chain-of-Thought (GVCoT), a unified framework that performs native visual reasoning by first generating spatial cues to localize the target region and then executing the edit. Unlike prior text-only CoT or tool-dependent visual CoT paradigms, GVCoT jointly optimizes visual tokens generated during the reasoning and editing phases in an end-to-end manner. This way fosters the emergence of innate spatial reasoning ability and enables more effective utilization of visual-domain cues. The main challenge of training GCVoT lies in the scarcity of large-scale editing data with precise edit region annotations; to this end, we construct GVCoT-Edit-Instruct, a dataset of 1.8M high-quality samples spanning 19 tasks. We adopt a progressive training strategy: supervised fine-tuning to build foundational localization ability in reasoning trace before final editing, followed by reinforcement learning to further improve reasoning and editing quality. Finally, we introduce SREdit-Bench, a new benchmark designed to comprehensively stress-test models under sophisticated scenes and fine-grained referring expressions. Experiments demonstrate that GVCoT consistently outperforms state-of-the-art models on SREdit-Bench and ImgEdit. We hope our GVCoT will inspire future research toward interpretable and precise image editing.
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。
