TextDestroyer:一种用于从图像中破坏异常文本的免训练和免标注扩散方法
TextDestroyer: A Training- and Annotation-Free Diffusion Method for Destroying Anomal Text from Images
AI总结:
本文提出TextDestroyer,首个免训练免标注的场景文本破坏扩散方法,通过三阶段分层获取掩码、扰乱潜在码并利用自注意力和反演潜在码替换实现完美背景恢复,彻底破坏文本且泛化性强。
摘要:
在本文中,我们提出了TextDestroyer,这是首个使用预训练扩散模型进行场景文本破坏的免训练和免标注方法。现有的场景文本去除模型需要复杂的标注和重新训练,并且可能会留下微弱但仍可识别的文本信息,从而损害隐私保护和内容隐藏。TextDestroyer通过采用三阶段分层过程来获取准确的文本掩码,从而解决了这些问题。我们的方法在重建之前使用高斯分布扰乱潜在起始码中的文本区域。在扩散去噪过程中,从原始潜在空间引用自注意力键和值以恢复受损的背景。在每个反演步骤中保存的潜在码用于在重建期间进行替换,确保完美的背景恢复。TextDestroyer的优势包括:(1)它消除了费力的数据标注和耗费资源的训练;(2)它实现了更彻底的文本破坏,防止可识别的痕迹;以及(3)它展示了更好的泛化能力,在真实世界场景和生成的图像上均表现良好。
英文摘要:
In this paper, we propose TextDestroyer, the first training- and annotation-free method for scene text destruction using a pre-trained diffusion model. Existing scene text removal models require complex annotation and retraining, and may leave faint yet recognizable text information, compromising privacy protection and content concealment. TextDestroyer addresses these issues by employing a three-stage hierarchical process to obtain accurate text masks. Our method scrambles text areas in the latent start code using a Gaussian distribution before reconstruction. During the diffusion denoising process, self-attention key and value are referenced from the original latent to restore the compromised background. Latent codes saved at each inversion step are used for replacement during reconstruction, ensuring perfect background restoration. The advantages of TextDestroyer include: (1) it eliminates labor-intensive data annotation and resource-intensive training; (2) it achieves more thorough text destruction, preventing recognizable traces; and (3) it demonstrates better generalization capabilities, performing well on both real-world scenes and generated images.
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。