无需配对数据即可精准擦除目标物体，避免生成无关内容。
You Only Erase Once: Erasing Anything without Bringing Unexpected Content
- 基于无配对真实图像训练扩散模型，结合实体分割与上下文一致性损失
- 在COCO、PASCAL VOC等数据集上实现零意外内容生成，质量优于现有方法
- 适合需要高保真图像编辑的视觉生成、内容创作场景
我们提出YOEO，一种物体擦除方法。不同于近期基于扩散模型的方法因缺乏足够配对训练数据和显式生成约束，常在掩码区域产生意外内容，本方法可在不引入无关物体或伪影的前提下，高质量完成物体擦除并忠实保持周围上下文连贯性。通过在仅含大规模真实图像的无配对数据上训练物体擦除扩散模型，并利用基于实体分割模型构建的杂项检测器与上下文一致性损失进行监督，实现该目标。为提升训练与推理效率，采用扩散蒸馏策略训练少步数擦除扩散模型。大量实验表明，该方法超越现有最优物体擦除方法。代码将发布于 https://zyxunh.github.io/YOEO-ProjectPage/。
原文摘要 · Abstract (English)
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. Code will be available at https://zyxunh.github.io/YOEO-ProjectPage/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。