水印图像可编辑吗?SafeMark用于水印保持的文本引导图像编辑
Are Watermarked Images Editable? SafeMark for Watermark-Preserving Text-Guided Image Editing
AI总结:
本文研究了一个基础但未被充分探索的问题:水印图像能否在不损害水印完整性的情况下保持可编辑?我们提出了SafeMark框架,该框架在图像编辑过程中显式地将水印完整性整合进去。具体来说,SafeMark将阈值化的水印解码损失直接添加到扩散编辑器的训练目标中,微调编辑器,使得语义上有效的编辑也能够在最终输出中保留嵌入的水印。这种设计具有清晰的信息论依据:在编辑图像上保持高比特准确性下限界了编辑通道所保持的水印与编辑输出之间的互信息,这一量根本控制着水印恢复能力。SafeMark与可微扩散编辑器兼容,不需要架构修改。在多个数据集、文本引导编辑方法和编辑后失真设置上的广泛评估表明,SafeMark在多种编辑设置中实现了高水印比特准确性,同时保持高质量的语义编辑,而不会牺牲对常见编辑后失真的鲁棒性。这些结果表明,语义可编辑性和水印完整性本质上是兼容的,使生成编辑管道中的图像溯源变得可信。
摘要:
本文研究了一个基础但未被充分探索的问题:水印图像能否在不损害水印完整性的情况下保持可编辑?我们提出了SafeMark,一个用于水印保持的文本引导图像编辑的框架,该框架在编辑过程中显式地整合水印完整性。具体来说,SafeMark将阈值化的水印解码损失直接添加到扩散编辑器的训练目标中,微调编辑器,使得语义上有效的编辑也能够在最终输出中保留嵌入的水印。这种设计具有清晰的信息论依据:在编辑图像上保持高比特准确性下限界了编辑通道所保持的水印与编辑输出之间的互信息,这一量根本控制着水印恢复能力。SafeMark与可微扩散编辑器兼容,且不需要架构修改。在多个数据集、文本引导编辑方法和编辑后失真设置上的广泛评估表明,SafeMark在多种编辑设置中实现了高水印比特准确性,同时保持高质量的语义编辑,而不会牺牲对常见编辑后失真的鲁棒性。这些结果表明,语义可编辑性和水印完整性本质上是兼容的,使生成编辑管道中的图像溯源变得可信。
英文摘要:
This paper investigates a fundamental yet underexplored question: can watermarked images remain editable without compromising watermark integrity? We propose SafeMark, a framework for watermark-preserving text-guided image manipulation that explicitly integrates watermark integrity into the editing process. Specifically, SafeMark adds a thresholded watermark-decoding loss directly to the diffusion editor's training objective, fine-tuning the editor so that semantically valid edits also preserve the embedded watermark at the final output. This design admits a clean information-theoretic justification: maintaining high bit-accuracy on the edited image lower-bounds the mutual information that the editor channel preserves between watermark and edited output, the quantity that fundamentally controls watermark recoverability. SafeMark is compatible with differentiable diffusion-based editors, and requires no architectural modification. Extensive evaluations across multiple datasets, text-guided editing methods, and post-edit distortion settings demonstrate that SafeMark achieves high watermark bit accuracy across diverse editing settings while maintaining high-quality semantic edits, without sacrificing robustness to common post-edit distortions. These results demonstrate that semantic editability and watermark integrity are fundamentally compatible, enabling trustworthy image provenance in generative editing pipelines.
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。