一次擦除即止：擦除任意目标而不引入意外内容
You Only Erase Once: Erasing Anything without Bringing Unexpected Content
用实体分割模型构建的杂物检测器与上下文一致性损失，在无配对真实图像上监督扩散模型做目标擦除，可直接迁移到 inpainting/物体移除任务的数据构造与约束设计；扩散蒸馏得到的少步擦除模型也为编辑类扩散模型的推理加速提供参考。
原文依据 training an object erasure diffusion model on unpaired data containing only large-scale real-world images
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 YOEO，一种用于目标擦除的方法。近期的扩散类方法由于缺乏足够的配对训练数据以及对内容生成的显式约束，往往难以在擦除目标对象的同时避免在掩码区域内生成意外内容；与之不同，我们的方法能够产生高质量的目标擦除结果，既不含多余对象或伪影，又忠实保持与周围内容整体的上下文连贯性。为实现这一目标，我们在仅包含大规模真实世界图像的无配对数据上训练目标擦除扩散模型，其监督信号来自一个杂物检测器以及一个基于实体分割模型构建的上下文连贯性损失。为支持更高效的训练与推理，我们采用扩散蒸馏策略训练少步擦除扩散模型。大量实验表明，我们的方法优于最优的目标擦除方法。代码见 https://zyxunh.github.io/YOEO-ProjectPage/。
英文原文摘要 1040 字符
We present YOEO, an approach for object erasure. Unlike recent diffusion-based methods which struggle to erase target objects without generating unexpected content within the masked regions due to lack of sufficient paired training data and explicit constraint on content generation, our method allows to produce high-quality object erasure results free of unwanted objects or artifacts while faithfully preserving the overall context coherence to the surrounding content. We achieve this goal by training an object erasure diffusion model on unpaired data containing only large-scale real-world images, under the supervision of a sundries detector and a context coherence loss that are built upon an entity segmentation model. To enable more efficient training and inference, a diffusion distillation strategy is employed to train for a few-step erasure diffusion model. Extensive experiments show that our method outperforms the state-of-the-art object erasure methods. Our code is available at https://zyxunh.github.io/YOEO-ProjectPage/.