Advanced image editing techniques, particularly inpainting, are essential for seamlessly removing unwanted elements while preserving visual integrity. Traditional GAN-based methods have achieved notable success, but recent advancements in diffusion models have produced superior results due to their training on large-scale datasets, enabling the generation of remarkably realistic inpainted images. Despite their strengths, diffusion models often struggle with object removal tasks without explicit guidance, leading to unintended hallucinations of the removed object. To address this issue, we introduce CLIPAway, a novel approach leveraging CLIP embeddings to focus on background regions while excluding foreground elements. CLIPAway enhances inpainting accuracy and quality by identifying embeddings that prioritize the background, thus achieving seamless object removal. Unlike other methods that rely on specialized training datasets or costly manual annotations, CLIPAway provides a flexible, plug-and-play solution compatible with various diffusion-based inpainting techniques.

翻译：先进的图像编辑技术，特别是图像修复，对于无缝移除不需要的元素同时保持视觉完整性至关重要。传统的基于GAN的方法已取得显著成功，但扩散模型的最新进展因其在大规模数据集上的训练而产生了更优的结果，能够生成极为逼真的修复图像。尽管具有这些优势，扩散模型在没有明确指导的情况下，常常难以处理物体移除任务，导致被移除物体出现意外的幻觉残留。为解决这一问题，我们提出了CLIPAway，这是一种利用CLIP嵌入来聚焦背景区域同时排除前景元素的新方法。CLIPAway通过识别优先关注背景的嵌入，从而提升修复的准确性和质量，实现无缝的物体移除。与其他依赖专门训练数据集或昂贵手动标注的方法不同，CLIPAway提供了一种灵活的即插即用解决方案，兼容各种基于扩散的图像修复技术。