mirror of
https://github.com/wiltodelta/remove-ai-watermarks.git
synced 2026-08-19 12:07:13 +02:00
Victor KuznetsovandClaude Opus 5
37789e02f6
Output stays bit-identical: decoder bits and detector verdicts recorded over 200 sampled data/ images plus two synthesized carriers before and after, and the record is byte-identical. Measured on a 1536x2816 image -- decoder 0.280s to 0.016s, warm identify() 1.757s to 1.365s with both arms timed in one process. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
1.0 KiB
1.0 KiB
Code provenance
This page records notices required by source dependencies and licensed derivative work.
Licensed derivative work
- The DWT-DCT implementation derives from ShieldMnt's
invisible-watermark, licensed under MIT. Its notice ships insrc/remove_ai_watermarks/licenses/invisible-watermark-MIT.txt. The decode path is a vectorized reformulation, not a transcription: it produces the same bits and is checked against upstream's own decoder, but it no longer corresponds line by line toimwatermark/maxDct.py. Diffing the two files will show structurally different code, which is expected and does not mean the derivation notice is stale.
Licensed test fixtures
data/fixtures/provenance/adobe-trustmark-p.pngis Adobe's official TrustMark Variant P example, licensed under MIT. Its source commit, digest, and reproduced license are recorded beside the fixture indata/fixtures/README.mdanddata/licenses/adobe-trustmark-MIT.txt.