SOURCE-LINKED INTELLIGENCE

RAIN: Region-Aware Inversion Network for Semantic Watermark Extraction

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Semantic watermarks for diffusion models embed ownership information into the generative process while preserving perceptual quality, but Gaussian-Shading extraction conventionally requires multi-step diffusion inversion to recover the initial noise. Recent one-step methods show that this cost can be reduced substantially. We study this problem through extended flow matching and conditional regression. The key observation is that, near the high-SNR image endpoint, recovering a useful noise statistic given by the first-step output of the extended flow matching in the high-SNR regime is much sim

Read original source ↗ Open in workspace

recordType

paper

region

Global