无需训练即可精准保留背景，实现自然融合的图像编辑
KV-Edit: Training-Free Image Editing for Precise Background Preservation
- 利用DiT中的KV缓存机制，直接复用原图背景特征
- 在用户指定区域生成新内容，背景一致性显著提升
- 兼容任意DiT模型，无需额外训练，内存开销恒定
背景一致性仍是图像编辑中的关键挑战。尽管已有大量研究，现有方法仍难以兼顾与原图的相似性与目标内容的契合度。本文提出KV-Edit，一种无需训练的方法，通过DiT中的KV缓存机制，保留背景特征而非重新生成，避免复杂机制和昂贵训练，使新内容在用户指定区域内与背景无缝融合。进一步分析了编辑过程中的内存消耗，采用无反演方法将空间复杂度优化至O(1)。该方法可适配任意基于DiT的生成模型，无需额外训练。实验表明，KV-Edit在背景一致性和图像质量上均显著优于现有方法，甚至超越部分训练型方法。
原文摘要 · Abstract (English)
Background consistency remains a significant challenge in image editing tasks. Despite extensive developments, existing works still face a trade-off between maintaining similarity to the original image and generating content that aligns with the target. Here, we propose KV-Edit, a training-free approach that uses KV cache in DiTs to maintain background consistency, where background tokens are preserved rather than regenerated, eliminating the need for complex mechanisms or expensive training, ultimately generating new content that seamlessly integrates with the background within user-provided regions. We further explore the memory consumption of the KV cache during editing and optimize the space complexity to $O(1)$ using an inversion-free method. Our approach is compatible with any DiT-based generative model without additional training. Experiments demonstrate that KV-Edit significantly outperforms existing approaches in terms of both background and image quality, even surpassing training-based methods. Project webpage is available at https://xilluill.github.io/projectpages/KV-Edit
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。