JND-Guided Neural Watermarking with Spatial Transformer Decoding for Screen-Capture Robustness

TL;DR

This paper introduces a deep learning framework for screen-capture robust watermarking that models realistic distortions, uses perceptual loss for imperceptibility, and includes automated decoding modules, achieving high-quality, robust watermarks.

Contribution

It presents a novel end-to-end approach with a comprehensive distortion simulation, perceptual loss, and automated localization for robust watermarking against complex screen-capture distortions.

Findings

Achieves an average PSNR of 30.94 dB and SSIM of 0.94 on watermarked images.

Successfully embeds 127-bit payloads with high perceptual quality.

Demonstrates robustness against realistic screen-capture distortions.

Abstract

Screen-shooting robust watermarking aims to imperceptibly embed extractable information into host images such that the watermark survives the complex distortion pipeline of screen display and camera recapture. However, achieving high extraction accuracy while maintaining satisfactory visual quality remains an open challenge, primarily because the screen-shooting channel introduces severe and entangled degradations including Moir\'{e} patterns, color-gamut shifts, perspective warping, and sensor noise. In this paper, we present an end-to-end deep learning framework that jointly optimizes watermark embedding and extraction for screen-shooting robustness. Our framework incorporates three key innovations: (i) a comprehensive noise simulation layer that faithfully models realistic screen-shooting distortions -- notably including a physically-motivated Moir\'{e} pattern generator -- enabling the network to learn robust representations against the full spectrum of capture-channel noise through adversarial training; (ii) a Just Noticeable Distortion (JND) perceptual loss function that adaptively modulates watermark embedding strength by supervising the perceptual discrepancy between the JND coefficient map and the watermark residual, thereby concentrating watermark energy in perceptually insensitive regions to maximize visual quality; and (iii) two complementary automatic localization modules -- a semantic-segmentation-based foreground extractor for captured image rectification and a symmetric noise template mechanism for anti-cropping region recovery -- that enable fully automated watermark decoding under realistic deployment conditions. Extensive experiments demonstrate that our method achieves an average PSNR of 30.94~dB and SSIM of 0.94 on watermarked images while embedding 127-bit payloads.