MarkCleaner: High-Fidelity Watermark Removal via Imperceptible Micro-Geometric Perturbation

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.

Key Contributions

• Demonstrates that semantic watermarks (e.g., TreeRing) are fundamentally vulnerable to micro-geometric perturbations that disrupt phase alignment in the Fourier-transformed latent space
• Proposes MarkCleaner, a mask-guided encoder + 2D Gaussian Splatting-based decoder framework trained on micro-geometry-perturbed supervision to remove watermarks while preserving visual fidelity
• Achieves superior watermark removal effectiveness and visual consistency compared to reconstruction-based and generation-based baselines, with efficient real-time inference

🛡️ Threat Analysis

Details

Similar Papers