TokenPure: Watermark Removal through Tokenized Appearance and Structural Guidance

• URL: http://arxiv.org/abs/2512.01314v1
• Date: Mon, 01 Dec 2025 06:15:51 GMT
• Title: TokenPure: Watermark Removal through Tokenized Appearance and Structural Guidance
• Authors: Pei Yang, Yepeng Liu, Kelly Peng, Yuan Gao, Yiren Song,
• Abstract summary: TokenPure is a Diffusion Transformer-based framework designed for effective and consistent watermark removal.<n>It reframes the task as conditional generation, entirely bypassing the initial watermark-carrying noise.<n>It achieves state-of-the-art watermark removal and reconstruction fidelity, substantially outperforming existing baselines in both perceptual quality and consistency.
• Score: 22.297964559583576
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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.

Related papers

• RecoverMark: Robust Watermarking for Localization and Recovery of Manipulated Faces [16.612226216769262]
  We propose RecoverMark, a watermarking framework that achieves robust manipulation localization, content recovery, and ownership verification simultaneously.<n>Our key insight is twofold. First, we exploit a critical real-world constraint: an adversary must preserve the background's semantic consistency to avoid visual detection.<n>Based on these insights, RecoverMark treats the protected face content itself as the watermark and embeds it into the surrounding background.
  arXiv  Detail & Related papers  (2026-02-24T07:11:40Z)
• RAVEN: Erasing Invisible Watermarks via Novel View Synthesis [35.417500510522835]
  In this work, we expose a fundamental vulnerability in invisible watermarks by reformulating watermark removal as a view synthesis problem.<n>Our key insight is that generating a perceptually consistent alternative view of the same semantic content, naturally removes the embedded watermark while preserving visual fidelity.<n>We introduce a zero-shot diffusion-based framework that applies controlled geometric transformations in latent space, augmented with view-guided correspondence attention to maintain structural consistency during reconstruction.
  arXiv  Detail & Related papers  (2026-01-13T18:59:58Z)
• ComMark: Covert and Robust Black-Box Model Watermarking with Compressed Samples [14.929889375744368]
  ComMark is a novel black-box model watermarking framework.<n>We show that ComMark achieves state-of-the-art performance in both covertness and robustness.<n>We extend its applicability beyond image recognition to tasks including speech recognition, sentiment analysis, image generation, image captioning, and video recognition.
  arXiv  Detail & Related papers  (2025-12-16T05:10:32Z)
• Watermarking Autoregressive Image Generation [4.335447827531541]
  Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance.<n>We present the first such approach by adapting language model watermarking techniques to this setting.<n>As our experiments demonstrate, our approach enables reliable and robust watermark detection with theoretically grounded p-values.
  arXiv  Detail & Related papers  (2025-06-19T14:25:51Z)
• Saliency-Aware Diffusion Reconstruction for Effective Invisible Watermark Removal [18.47018538990973]
  This paper introduces a novel Saliency-Aware Diffusion Reconstruction framework for watermark elimination on the web.<n>SADRE disrupts embedded watermarks by injecting targeted noise into latent representations guided by saliency masks.<n>A reverse diffusion process ensures high-fidelity image restoration, leveraging adaptive noise levels determined by watermark strength.
  arXiv  Detail & Related papers  (2025-04-17T10:15:10Z)
• Bridging Knowledge Gap Between Image Inpainting and Large-Area Visible Watermark Removal [57.84348166457113]
  We introduce a novel feature adapting framework that leverages the representation capacity of a pre-trained image inpainting model.<n>Our approach bridges the knowledge gap between image inpainting and watermark removal by fusing information of the residual background content beneath watermarks into the inpainting backbone model.<n>For relieving the dependence on high-quality watermark masks, we introduce a new training paradigm by utilizing coarse watermark masks to guide the inference process.
  arXiv  Detail & Related papers  (2025-04-07T02:37:14Z)
• On the Coexistence and Ensembling of Watermarks [93.15379331904602]
  We find that various open-source watermarks can coexist with only minor impacts on image quality and decoding robustness.<n>We show how ensembling can increase the overall message capacity and enable new trade-offs between capacity, accuracy, robustness and image quality, without needing to retrain the base models.
  arXiv  Detail & Related papers  (2025-01-29T00:37:06Z)
• IWN: Image Watermarking Based on Idempotency [0.0]
  This paper explores the prospects of introducing idempotency into image watermark processing. The proposed model, which focuses on enhancing the recovery quality of color image watermarks, leverages idempotency to ensure superior image reversibility.
  arXiv  Detail & Related papers  (2024-09-29T01:29:34Z)
• Certifiably Robust Image Watermark [57.546016845801134]
  Generative AI raises many societal concerns such as boosting disinformation and propaganda campaigns. Watermarking AI-generated content is a key technology to address these concerns. We propose the first image watermarks with certified robustness guarantees against removal and forgery attacks.
  arXiv  Detail & Related papers  (2024-07-04T17:56:04Z)
• Removing Interference and Recovering Content Imaginatively for Visible Watermark Removal [63.576748565274706]
  This study introduces the Removing Interference and Recovering Content Imaginatively (RIRCI) framework. RIRCI embodies a two-stage approach: the initial phase centers on discerning and segregating the watermark component, while the subsequent phase focuses on background content restoration. To achieve meticulous background restoration, our proposed model employs a dual-path network capable of fully exploring the intrinsic background information beneath semi-transparent watermarks.
  arXiv  Detail & Related papers  (2023-12-22T02:19:23Z)
• Robust Identity Perceptual Watermark Against Deepfake Face Swapping [9.402982368385569]
  Deepfake face swapping has caused critical privacy issues with the rapid development of deep generative models.<n>We propose a robust identity perceptual watermarking framework that concurrently performs detection and source tracing against Deepfake face swapping.
  arXiv  Detail & Related papers  (2023-11-02T16:04:32Z)
• T2IW: Joint Text to Image & Watermark Generation [74.20148555503127]
  We introduce a novel task for the joint generation of text to image and watermark (T2IW) This T2IW scheme ensures minimal damage to image quality when generating a compound image by forcing the semantic feature and the watermark signal to be compatible in pixels. We demonstrate remarkable achievements in image quality, watermark invisibility, and watermark robustness, supported by our proposed set of evaluation metrics.
  arXiv  Detail & Related papers  (2023-09-07T16:12:06Z)
• Watermarking Images in Self-Supervised Latent Spaces [75.99287942537138]
  We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches. We present a way to embed both marks and binary messages into their latent spaces, leveraging data augmentation at marking time.
  arXiv  Detail & Related papers  (2021-12-17T15:52:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.