mirror of
https://github.com/wiltodelta/remove-ai-watermarks.git
synced 2026-08-09 23:50:40 +02:00
Victor KuznetsovandClaude Opus 5
78d9e81d0f
The visible-mark path had grown three copies of one ladder sweep, four
near-identical `detect` arms, and four hand-rolled `footprint_mask` overrides;
mark knowledge sat in five hand-maintained tables across three modules; and the
flagship `all`/`batch` pipeline existed only in cli.py, written twice with
divergent behavior.
Detection is now one measurement. `_ladder_best` replaces the three sweeps,
`_scan`/`_verdict` replace the four arms, and the winning box travels to the
mask on `TextMarkDetection.match_box` instead of being swept a second time.
`detect_both` returns the strict and relaxed verdicts from one scan, which
halves the arbiter's perception cost (260 -> 130 matchTemplate calls on a 2048²
image, verdicts identical field for field). A per-mark demotion goes in the new
`_post_gate` hook, never in a `detect` override -- an override is invisible to
the single-pass path, which is how the RunningHub and Yuanbao anchor gates
briefly stopped applying.
Everything about a mark is now one registry row: product, label regime, the
platform sentence `identify` reports, the metadata signals that confirm it, and
its TC260 producer codes. `identify._VISIBLE_MARK_PLATFORM`, the signal mapping
in `api.visible_provenance`, `_PRODUCT_OF` and the pill veto are derived from
those rows.
`api.remove_all` / `api.remove_batch` are the library form of the `all` and
`batch` commands; the CLI is a wrapper that owns console text and exit codes.
Progress is a `(stage, detail)` pair of stable tokens, so the CLI keys its
wording off structure rather than parsing the library's prose back.
Two intentional behavior changes, both verified against a recorded 811-image
sample of detector verdicts, removal-mask hashes, arbiter decisions and
`identify` reports:
* A TC260 label now relaxes the vendor its `ContentProducer` names rather than
ByteDance's pair on every China-AIGC image. 333 of 811 samples move; on 185
of them the previously relaxed pair was simply the wrong vendor, and the
mark actually present never reached the relaxed gate its own
`provenance_ncc_factor` was calibrated for.
* A confident LibLibAI detection suppresses the Jimeng pill, like every other
TC260 product's mark. It was registered alongside RunningHub and Baidu, both
of which were added to the hand-written veto list, and it was not. 1 sample
moves, and it is exactly the co-firing case.
Nothing else in that record changes: detector verdicts, mask hashes and
`identify` verdicts are byte-identical, and all 200 calibration constants are
untouched.
Also: `aigc_label` and friends plus `extract_c2pa_info` are memoized on
(path, mtime_ns, size) -- size because this package rewrites in place; the
native TC260 container readers route on magic bytes instead of the file
extension, so a mislabeled AVI or FLV is no longer invisible; `identify` shares
one pixel decode between the DWT-DCT and visible stages (TrustMark keeps its own
Pillow decode, which is not substitutable); and the six `stabilize_*` video
wrappers collapse into one policy table.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
121 lines
3.8 KiB
Python
121 lines
3.8 KiB
Python
"""Tencent Yuanbao visible watermark detector and localizer.
|
|
|
|
Yuanbao stamps a compact italic two-line mark, ``元宝`` over ``AI生成``, in the
|
|
bottom-right corner. The same silhouette is rendered light on dark scenes and
|
|
dark on pale scenes, so a one-polarity white top-hat cannot detect it reliably.
|
|
This engine uses the shared text-mark pipeline with the ``contrast`` front-end:
|
|
normalized absolute local-luma residual followed by silhouette NCC.
|
|
|
|
The bundled silhouette is synthetic and font-rendered by
|
|
``scripts/render_vendor_silhouettes.py``. Removal follows the shared
|
|
localize-then-fill path and uses the detector's own match box.
|
|
|
|
Calibration (2026-07-25) used the metadata-harvested Tencent cohort after byte
|
|
deduplication and visual adjudication. The standard two-line variant was detected
|
|
on 26 of 28 unique marked carriers (92.9%) at gate 0.38, with 0 fires on 286
|
|
hand-labeled clean frames. The separate photographer-overlay variant is not
|
|
covered by this silhouette.
|
|
"""
|
|
|
|
# The module-level helpers are imported by tests.
|
|
# pyright: reportUnusedFunction=false
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from typing import TYPE_CHECKING, Any
|
|
|
|
from remove_ai_watermarks import _text_mark_engine
|
|
from remove_ai_watermarks._text_mark_engine import (
|
|
TextMarkConfig,
|
|
TextMarkDetection,
|
|
TextMarkEngine,
|
|
TextMarkScan,
|
|
)
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
if TYPE_CHECKING:
|
|
from numpy.typing import NDArray
|
|
|
|
WM_WIDTH_FRAC = 0.20
|
|
WM_HEIGHT_FRAC = 0.15
|
|
MARGIN_RIGHT_FRAC = 0.002
|
|
MARGIN_BOTTOM_FRAC = 0.002
|
|
|
|
MAX_SATURATION = 55
|
|
LOGO_MIN_LUMA = 150
|
|
TOPHAT_DELTA = 12
|
|
|
|
DETECT_MIN_COVERAGE = 0.04
|
|
DETECT_NCC_THRESHOLD = 0.38
|
|
|
|
_ALPHA_WIDTH_FRAC = 0.08
|
|
_ALPHA_HEIGHT_FRAC = 0.0446
|
|
_LADDER = (0.95, 1.0, 1.05)
|
|
|
|
_CONFIG = TextMarkConfig(
|
|
name="Tencent Yuanbao",
|
|
asset_name="yuanbao_alpha.png",
|
|
corner="br",
|
|
margin_floor=4,
|
|
width_frac=WM_WIDTH_FRAC,
|
|
height_frac=WM_HEIGHT_FRAC,
|
|
margin_x_frac=MARGIN_RIGHT_FRAC,
|
|
margin_bottom_frac=MARGIN_BOTTOM_FRAC,
|
|
max_saturation=MAX_SATURATION,
|
|
logo_min_luma=LOGO_MIN_LUMA,
|
|
tophat_delta=TOPHAT_DELTA,
|
|
morph_open_size=5,
|
|
detect_min_coverage=DETECT_MIN_COVERAGE,
|
|
detect_ncc_threshold=DETECT_NCC_THRESHOLD,
|
|
detect_frontend="contrast",
|
|
scale_basis="short",
|
|
ladder=_LADDER,
|
|
alpha_width_frac=_ALPHA_WIDTH_FRAC,
|
|
alpha_height_frac=_ALPHA_HEIGHT_FRAC,
|
|
min_gw=32,
|
|
provenance_ncc_factor=1.0,
|
|
)
|
|
|
|
|
|
def _alpha_template() -> NDArray[Any] | None:
|
|
"""The bundled Yuanbao alpha template (float [0,1]), or None."""
|
|
return _text_mark_engine.load_alpha_template(_CONFIG.asset_name)
|
|
|
|
|
|
class YuanbaoEngine(TextMarkEngine):
|
|
"""Detect and localize the bottom-right Yuanbao mark."""
|
|
|
|
_ANCHOR_MAX_RIGHT = 0.04
|
|
_ANCHOR_MAX_BOTTOM = 0.04
|
|
|
|
def __init__(self) -> None:
|
|
super().__init__(_CONFIG)
|
|
|
|
def _post_gate(self, det: TextMarkDetection, scan: TextMarkScan) -> TextMarkDetection:
|
|
"""Demote a match that does not hug the bottom-right corner.
|
|
|
|
A shared post-gate rather than a ``detect`` override, so the single-pass
|
|
perception path (``detect_both``) cannot skip it.
|
|
"""
|
|
if not det.detected or scan.loc is None:
|
|
return det
|
|
box = det.match_box # the sweep the scan already ran on this same loc
|
|
if box is None:
|
|
det.detected = False
|
|
return det
|
|
h, w = scan.frame
|
|
base = min(h, w)
|
|
right = (w - (scan.loc.x + box[2] + 1)) / base
|
|
bottom = (h - (scan.loc.y + box[3] + 1)) / base
|
|
if not (0 <= right <= self._ANCHOR_MAX_RIGHT and 0 <= bottom <= self._ANCHOR_MAX_BOTTOM):
|
|
logger.debug(
|
|
"Yuanbao detect: score %.3f but match off-anchor (right=%.3f bottom=%.3f); demoting.",
|
|
det.confidence,
|
|
right,
|
|
bottom,
|
|
)
|
|
det.detected = False
|
|
return det
|