通过微几何扰动实现水印无损清除，不破坏图像语义内容。
MarkCleaner: High-Fidelity Watermark Removal via Imperceptible Micro-Geometric Perturbation
- 利用微小空间位移打乱水印相位，实现非再生式清除
- 在保持语义一致的前提下，去除率超90%且视觉保真度高
- 适合需要精准去水印的数字版权管理场景
语义水印对常规图像空间攻击具有强鲁棒性。本文发现，这种鲁棒性在微几何扰动下会失效：空间位移可破坏相位对齐从而移除水印。受此启发，我们提出MarkCleaner框架，避免基于重生成的去水印带来的语义漂移。该框架采用微几何扰动监督训练，使模型分离语义内容与严格的空间对齐，实现对细微几何偏移的鲁棒重建。其包含掩码引导编码器以学习显式空间表示，以及基于2D高斯点云的解码器，能显式参数化几何扰动同时保留语义信息。大量实验表明，MarkCleaner在去水印有效性与视觉保真度方面均表现卓越，并支持高效实时推理。代码将在录用后公开。
原文摘要 · Abstract (English)
Semantic watermarks exhibit strong robustness against conventional image-space attacks. In this work, we show that such robustness does not survive under micro-geometric perturbations: spatial displacements can remove watermarks by breaking the phase alignment. Motivated by this observation, we introduce MarkCleaner, a watermark removal framework that avoids semantic drift caused by regeneration-based watermark removal. Specifically, MarkCleaner is trained with micro-geometry-perturbed supervision, which encourages the model to separate semantic content from strict spatial alignment and enables robust reconstruction under subtle geometric displacements. The framework adopts a mask-guided encoder that learns explicit spatial representations and a 2D Gaussian Splatting-based decoder that explicitly parameterizes geometric perturbations while preserving semantic content. Extensive experiments demonstrate that MarkCleaner achieves superior performance in both watermark removal effectiveness and visual fidelity, while enabling efficient real-time inference. Our code will be made available upon acceptance.
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。