RAIN: Redundancy-Aware Latent Injection for Quality-Preserving Image Watermarking

Diffusion models have gained widespread adoption due to their ability to generate highly realistic images, yet their rapid proliferation also raises security and traceability concerns. To address issues of ownership verification and accountability, current watermarking techniques primarily focus on embedding information into the internal mechanisms of generative pipelines. Nevertheless, many existing methods inject watermarks directly into latent representations without adequately exploiting inherent redundancies or perceptual properties in latent space, leading to degraded image quality. In this work, we conduct a systematic analysis aimed at quantifying differentiated redundancies present within latent space, and further propose a novel Redundancy-Aware Latent Injection framework RAIN based on the above analysis. Specifically, a redundancy‑aware adaptive watermark fusion method is introduced to preserve image quality, which utilizes the differentiated redundancy distribution to guide adaptive watermark allocation in different perception tolerance regions. Moreover, a distribution alignment initialization strategy is designed to align the watermark’s initial distribution to the latent prior, reducing initialization bias and improving convergence efficiency. Comprehensive experimental evaluations demonstrate that RAIN achieves state-of-the-art performance by delivering superior perceptual quality under high-capacity watermarking scenarios.

Authors

• Yehan Sun Institute of Information Science, Beijing Jiaotong University Visual Intelligence +X International Cooperation Joint Laboratory of MOE
• Rongrong Ni Institute of Information Science, Beijing Jiaotong University Visual Intelligence +X International Cooperation Joint Laboratory of MOE
• Chuangchuang Tan Institute of Information Science, Beijing Jiaotong University Visual Intellgence +X International Cooperation Joint Laboratory of MOE
• Huan Liu Institute of Information Science, Beijing Jiaotong University Visual Intellgence +X International Cooperation Joint Laboratory of MOE
• Wenhao Ni Institute of Information Science, Beijing Jiaotong University Visual Intelligence +X International Cooperation Joint Laboratory of MOE
• Renshuai Tao Institute of Information Science, Beijing Jiaotong University Visual Intellgence +X International Cooperation Joint Laboratory of MOE
• Yao Zhao Institute of Information Science, Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology

Keywords

No keywords are indexed for this paper.