remove-ai-watermarks

mirror of https://github.com/wiltodelta/remove-ai-watermarks.git synced 2026-07-04 23:47:49 +02:00

Files

T

Victor Kuznetsov 3f5d6a0af1 docs(landscape): back the DWT-DCT positive-only limitation with researched root cause + citations

Deep-research (2026-06-19, adversarially verified) confirms the open imwatermark
dwtDct mark is fragile by scheme, not by our usage: maintainers admit no 100%
clean-decode guarantee; measured ~0.79 bit accuracy clean (~38/48, below our 44
gate). Root causes (code-verified + locally reproduced): per-block max-coefficient
bit read (content flips bits) and YUV chroma 8-bit clamping on bright pixels (the
bright-flat / all-ones failure). No maintained fork or detector does this scheme
reliably (WAVES relegates it to an appendix; learned schemes are a different class;
dwtDctSvd cannot decode SDXL's dwtDct). Conclusion: keep it positive-only, rely on
C2PA. Sources: imwatermark READMEs, arXiv:2406.08337 (WMAdapter), arXiv:2401.08573
(WAVES), diffusers SDXL watermark.py.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-19 10:27:08 -07:00

controlnet-removal-pipeline-research.md

docs(restore): document that restore methods REGENERATE, not preserve

2026-06-08 21:08:11 -07:00

known-limitations.md

lower(strength): drop vendor-adaptive floor to OpenAI 0.10 / Google 0.15

2026-06-14 13:17:11 -07:00

module-internals.md

perf(text-mark): footprint-sized arrays in reverse-alpha CPU path

2026-06-19 10:01:07 -07:00

release-and-distribution.md

Slim CLAUDE.md: move module internals, limitations, landscape research to docs