TokenPure: Watermark Removal through Tokenized Appearance and Structural Guidance
This addresses the challenge of robust watermark removal for digital content, such as AI-generated assets, with incremental improvements in method design.
The paper tackles the problem of removing watermarks from images while preserving content quality, introducing TokenPure, a Diffusion Transformer-based framework that achieves state-of-the-art performance in watermark removal and reconstruction fidelity, substantially outperforming existing baselines.
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.