Bootstrap Your Generator: 基于流匹配的无配对视觉编辑
Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching
AI总结：
提出Bootstrap Your Generator (ByG)框架，利用基础模型知识通过流匹配实现无配对训练的图像视频编辑，无需外部信号，在数据稀缺场景下达到最优性能。
摘要：
现代生成模型对视觉内容有深刻理解，但训练它们进行图像编辑通常需要大量配对示例数据集。这限制了可扩展性，尤其是对于视频编辑，收集配对数据成本过高。我们提出了Bootstrap Your Generator (ByG)，一个用于流匹配编辑模型无配对训练的通用框架。它利用基础模型的知识，无需任何外部信号。我们的方法将从冻结模型中提取的指令遵循线索与用于结构保持的循环一致性相结合。为了使这可行，我们提出将来自干净预测的下游损失的梯度路由到噪声训练状态。我们在具有挑战性的数据稀缺图像和视频编辑场景中展示了最先进的结果。大量评估和用户研究表明，我们的方法有效泛化到未见过的领域，并优于在数百万样本上训练的监督基线。分析表明，我们的梯度路由弥合了训练-推理差距，从基础模型中提取语义线索提供了强大的训练信号，消除了对外部奖励模型的需求。
英文摘要：
Modern generative models possess a deep understanding of visual content, yet training them for image editing typically requires massive datasets of paired examples. This limits scalability, especially for video editing where collecting paired data is prohibitively expensive. We propose Bootstrap Your Generator (ByG), a general framework for unpaired training of flow matching editing models. It leverages the base model's knowledge without any external signal. Our approach pairs instruction-following cues extracted from the frozen model with cycle-consistency for structure preservation. To make this tractable, we propose to route gradients from downstream losses over clean predictions to noisy training states. We demonstrate state-of-the-art results on challenging data-scarce image and video editing scenarios. Extensive evaluations and user studies show that our method effectively generalizes to unseen domains and outperforms supervised baselines trained on millions of samples. Analysis reveals that our gradient routing bridges the train-inference gap, and extracting semantic cues from a base model provides a robust training signal that obviates the need for external reward models.
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。
