ProductConsistency：通过SFT和RL改进基于指令的图像编辑中的产品身份保持
ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL
AI总结：
针对基于指令的图像编辑中产品特征保持不足的问题，提出ProductConsistency数据集和循环一致性奖励，结合监督微调与强化学习，显著提升产品一致性、文本渲染和视觉质量。
摘要：
近期基于指令的图像编辑的进展使模型能够根据自然语言指令执行复杂的视觉编辑。然而，在以产品为中心的场景中，保留产品特征、品牌和文本元素至关重要，当前的开源和闭源模型往往难以维持这种细粒度的对象身份。这一问题因缺乏具有文本保真度约束的基于指令的产品图像编辑数据集而进一步加剧，导致该能力在很大程度上被视为基于指令的图像编辑模型的隐式能力。在这项工作中，我们引入了ProductConsistency数据集，旨在改进以产品为中心的图像编辑。我们的方法包括一个用于产品编辑的包含87k样本的监督微调（SFT）数据集、一个包含869张独特产品图像的强化学习（RL）数据集，以及一个新的基准数据集ProductConsistency Benchmark，以允许对编辑模型进行严格和标准化的评估。为了指导RL训练，我们提出了一种循环一致性奖励，通过使用原始产品描述与从编辑图像生成的描述之间的字幕相似性来强制保持产品身份的语义。我们使用我们的数据集对Qwen-Image-Edit-2511和Flux.1-Kontext-dev进行了微调，并在OCR和感知指标以及基于MLLM的评估中展示了相对于基线模型的一致改进，表明更强的产品一致性、文本渲染和整体视觉质量；其中Qwen-Image-Edit-2511模型实现了字符错误率降低5倍。代码和流程可在此https URL获取。
英文摘要：
Recent advances in instruction-based image editing have enabled models to perform complex visual edits from natural language instructions. However, in product-centric scenarios where preserving product features, branding, and textual elements are critical, current open and closed source models often struggle to maintain this fine-grained object identity. This issue is further compounded by the lack of datasets for instruction-based product image editing with text fidelity constraints, leaving it largely treated as an implicit capability of instruction-based image editing models. In this work, we introduce the ProductConsistency dataset which is designed to improve product-centric image editing. Our approach includes a supervised fine-tuning (SFT) dataset of 87k samples for product editing, a reinforcement learning (RL) dataset with 869 unique product images, and a new benchmark dataset, the ProductConsistency Benchmark, to allow rigorous and standardized evaluation of editing models. To guide RL training, we propose a Cyclic Consistency reward that enforces semantic preservation of product identity by using caption similarity between the original product description and captions generated from the edited image. We fine-tune both Qwen-Image-Edit-2511 and Flux.1-Kontext-dev using our dataset and demonstrate consistent improvements over baseline models in OCR and Perceptual metrics, and MLLM-based evaluations as well, indicating stronger product consistency, text rendering, and overall visual quality; with the Qwen-Image-Edit-2511 model achieving a 5x reduction in the character error rate. The code and pipeline is available at https://anonymous.4open.science/r/ProductConsistency-6FCC/README.md
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。
