rohitrango/automatic-watermark-detection

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1263 stars · 397 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python implementation of the CVPR 2017 paper 'On The Effectiveness Of Visible Watermarks' that detects and removes visible watermarks from collections of images. It estimates the watermark and its alpha matte by exploiting consistency across multiple watermarked images, then reconstructs clean images via Poisson reconstruction.

Use cases

• remove visible watermarks from a batch of images
• detect watermark location in images
• estimate watermark alpha matte
• reproduce the CVPR 2017 watermark removal paper
• clean watermarked stock photo datasets

When to choose

• you have many images sharing the same watermark
• you want a research-grade Python implementation of the Dekel et al. CVPR 2017 algorithm
• you need watermark detection plus image reconstruction in numpy/scipy

When to avoid

• you need to remove a watermark from a single image (the algorithm needs multiple images)
• you want a production-supported tool with a license and active maintenance
• you need robustness against novel or semi-transparent watermark types

Facets

library · maturity maintenance

image-processing computer-vision computer-vision image-processing python cross-platform watermark-removal watermark-detection poisson-reconstruction image-matting research-project jupyter-notebook

Member repositories

For agents

markdown · JSON · MCP: product_card(name="rohitrango/automatic-watermark-detection")