mirror of
https://github.com/wiltodelta/remove-ai-watermarks.git
synced 2026-07-12 11:06:33 +02:00
Victor Kuznetsov
b579385c6f
The FP gate demotes a low-gradient match, but a real FAINT sparkle also has soft edges, so metadata-stripped faint sparkles were dropped. Keep a low-grad match that is a strong (conf >= 0.52), bright, near-WHITE-core sparkle: a real sparkle core is white, a clean bright corner that shape-matches (sky/sun) is colored (_core_saturation). Recovers ~14/20 stripped faint sparkles under the DEFAULT strict/auto (no metadata, no flag) at ~1.25% clean false-fire (baseline 0.55%); the ~0.51-scoring bright-background FPs stay demoted (below 0.52). A learned classifier on the same features measured WORSE than the tuned gate (tier-1: MLP 86.7% recall vs the gate's 90.8% at equal false-fire), so the heuristic stays; a patch-CNN with richer features is roadmapped P2 with low expected value -- the precision/recall wall is fundamental (deep-research + tier-1 both confirm it). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>