Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal.
Xiaodong CunChi-Man PunPublished in: CoRR (2020)
Keyphrases
- single image
- multiple images
- shape recovery
- d scene
- image pairs
- digital images
- super resolution
- light source
- shadow regions
- shape from shading
- partially occluded
- watermarking scheme
- spherical harmonics
- visual attention
- watermarking algorithm
- scene geometry
- manhattan world
- digital watermarking
- watermark extraction
- spatial domain
- image classification
- input image