AI RESEARCH
JND-Guided Neural Watermarking with Spatial Transformer Decoding for Screen-Capture Robustness
arXiv CS.CV
•
ArXi:2603.26766v1 Announce Type: new 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