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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kong, Xiaoxi, Yuan, Jieyu, Chen, Pengdi, Zhang, Yuanlin, Li, Chongyi, Li, Bin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910008383373312
author Kong, Xiaoxi
Yuan, Jieyu
Chen, Pengdi
Zhang, Yuanlin
Li, Chongyi
Li, Bin
author_facet Kong, Xiaoxi
Yuan, Jieyu
Chen, Pengdi
Zhang, Yuanlin
Li, Chongyi
Li, Bin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_01513
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MarkCleaner: High-Fidelity Watermark Removal via Imperceptible Micro-Geometric Perturbation
Kong, Xiaoxi
Yuan, Jieyu
Chen, Pengdi
Zhang, Yuanlin
Li, Chongyi
Li, Bin
Image and Video Processing
Artificial Intelligence
Cryptography and Security
Computer Vision and Pattern Recognition
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.
title MarkCleaner: High-Fidelity Watermark Removal via Imperceptible Micro-Geometric Perturbation
topic Image and Video Processing
Artificial Intelligence
Cryptography and Security
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.01513