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

TL;DR

MarkCleaner is a novel framework that effectively removes semantic watermarks by leveraging micro-geometric perturbations, enabling robust and high-fidelity watermark removal under subtle geometric displacements.

Contribution

It introduces a micro-geometry-perturbed training approach and a mask-guided encoder with Gaussian Splatting decoder for improved watermark removal.

Findings

Achieves superior watermark removal effectiveness.

Maintains high visual fidelity.

Enables real-time inference.

Abstract

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.