Visible Watermark Removal via Self-calibrated Localization and Background Refinement

TL;DR

This paper introduces a two-stage multi-task network for visible watermark removal that improves watermark localization accuracy and background texture quality through self-calibration and feature refinement.

Contribution

It proposes a novel two-stage approach with self-calibrated localization and multi-level feature refinement to enhance watermark removal performance.

Findings

Effective watermark localization and background restoration demonstrated on two datasets.

Improved texture quality of restored backgrounds compared to existing methods.

The method outperforms prior approaches in accuracy and visual quality.

Abstract

Superimposing visible watermarks on images provides a powerful weapon to cope with the copyright issue. Watermark removal techniques, which can strengthen the robustness of visible watermarks in an adversarial way, have attracted increasing research interest. Modern watermark removal methods perform watermark localization and background restoration simultaneously, which could be viewed as a multi-task learning problem. However, existing approaches suffer from incomplete detected watermark and degraded texture quality of restored background. Therefore, we design a two-stage multi-task network to address the above issues. The coarse stage consists of a watermark branch and a background branch, in which the watermark branch self-calibrates the roughly estimated mask and passes the calibrated mask to background branch to reconstruct the watermarked area. In the refinement stage, we integrate multi-level features to improve the texture quality of watermarked area. Extensive experiments on two datasets demonstrate the effectiveness of our proposed method.