TokenPure: Watermark Removal through Tokenized Appearance and Structural Guidance

TL;DR

TokenPure is a diffusion transformer-based framework that effectively removes watermarks from images by leveraging tokenized appearance and structural guidance, achieving state-of-the-art results in fidelity and consistency.

Contribution

It introduces a novel token-based conditional reconstruction approach for watermark removal, bypassing initial noise and enhancing content integrity.

Findings

Outperforms existing methods in watermark removal quality

Maintains high structural and perceptual fidelity

Demonstrates robustness against various watermark types

Abstract

In the digital economy era, digital watermarking serves as a critical basis for ownership proof of massive replicable content, including AI-generated and other virtual assets. Designing robust watermarks capable of withstanding various attacks and processing operations is even more paramount. We introduce TokenPure, a novel Diffusion Transformer-based framework designed for effective and consistent watermark removal. TokenPure solves the trade-off between thorough watermark destruction and content consistency by leveraging token-based conditional reconstruction. It reframes the task as conditional generation, entirely bypassing the initial watermark-carrying noise. We achieve this by decomposing the watermarked image into two complementary token sets: visual tokens for texture and structural tokens for geometry. These tokens jointly condition the diffusion process, enabling the framework to synthesize watermark-free images with fine-grained consistency and structural integrity. Comprehensive experiments show that TokenPure achieves state-of-the-art watermark removal and reconstruction fidelity, substantially outperforming existing baselines in both perceptual quality and consistency.