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>
298 lines
12 KiB
Python
298 lines
12 KiB
Python
"""Tests for the universal region eraser."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import numpy as np
|
|
import pytest
|
|
|
|
from remove_ai_watermarks.region_eraser import boxes_to_mask, erase, lama_available, migan_available
|
|
|
|
|
|
class TestPaddedCropBox:
|
|
"""The padded bounding box that bounds the learned backends' ONNX working set."""
|
|
|
|
def test_empty_mask_returns_none(self):
|
|
from remove_ai_watermarks.region_eraser import _padded_crop_box
|
|
|
|
assert _padded_crop_box(np.zeros((100, 100), np.uint8), 100, 100, pad_frac=0.1, pad_min=8) is None
|
|
|
|
def test_pad_min_dominates_and_clamps_at_border(self):
|
|
from remove_ai_watermarks.region_eraser import _padded_crop_box
|
|
|
|
mask = np.zeros((100, 100), np.uint8)
|
|
mask[0:5, 0:5] = 255 # 5-px mark in the top-left corner
|
|
# pad = max(8, int(0.1*5)) = 8; x0 clamps to 0 (not -8), x1 = min(100, 4+1+8) = 13.
|
|
assert _padded_crop_box(mask, 100, 100, pad_frac=0.1, pad_min=8) == (0, 0, 13, 13)
|
|
|
|
def test_pad_frac_dominates_for_large_mark(self):
|
|
from remove_ai_watermarks.region_eraser import _padded_crop_box
|
|
|
|
mask = np.zeros((400, 400), np.uint8)
|
|
mask[100:300, 100:300] = 255 # 200-px span
|
|
# pad = max(8, int(0.2*200)) = 40; box = (100-40, .., 299+1+40, ..).
|
|
assert _padded_crop_box(mask, 400, 400, pad_frac=0.2, pad_min=8) == (60, 60, 340, 340)
|
|
|
|
def test_clamps_at_far_border(self):
|
|
from remove_ai_watermarks.region_eraser import _padded_crop_box
|
|
|
|
mask = np.zeros((50, 60), np.uint8)
|
|
mask[45:50, 55:60] = 255 # bottom-right corner
|
|
_x0, _y0, x1, y1 = _padded_crop_box(mask, 50, 60, pad_frac=0.1, pad_min=8)
|
|
assert x1 == 60 # clamped to w, no overflow
|
|
assert y1 == 50 # clamped to h, no overflow
|
|
|
|
|
|
class TestBoxesToMask:
|
|
def test_mask_set_inside_box(self):
|
|
mask = boxes_to_mask((100, 100), [(10, 20, 30, 40)], dilate=0)
|
|
assert mask[25, 15] == 255 # inside
|
|
assert mask[0, 0] == 0 # outside
|
|
assert mask.shape == (100, 100)
|
|
|
|
def test_multiple_boxes(self):
|
|
mask = boxes_to_mask((100, 100), [(0, 0, 10, 10), (90, 90, 10, 10)], dilate=0)
|
|
assert mask[5, 5] == 255
|
|
assert mask[95, 95] == 255
|
|
assert mask[50, 50] == 0
|
|
|
|
def test_dilate_grows_mask(self):
|
|
m0 = boxes_to_mask((100, 100), [(40, 40, 10, 10)], dilate=0)
|
|
m5 = boxes_to_mask((100, 100), [(40, 40, 10, 10)], dilate=5)
|
|
assert m5.sum() > m0.sum()
|
|
|
|
def test_box_clipped_to_bounds(self):
|
|
# box partly outside the image must not raise and stays in-bounds
|
|
mask = boxes_to_mask((50, 50), [(40, 40, 100, 100)], dilate=0)
|
|
assert mask[45, 45] == 255
|
|
|
|
|
|
class TestEraseCv2:
|
|
def _image_with_logo(self) -> tuple[np.ndarray, tuple[int, int, int, int]]:
|
|
img = np.full((200, 200, 3), 120, np.uint8) # flat gray background
|
|
box = (140, 160, 50, 30)
|
|
x, y, w, h = box
|
|
img[y : y + h, x : x + w] = (255, 255, 255) # bright "logo"
|
|
return img, box
|
|
|
|
def test_erase_changes_region(self):
|
|
img, box = self._image_with_logo()
|
|
out = erase(img, boxes=[box], backend="cv2")
|
|
x, y, w, h = box
|
|
# on a flat background the logo region should be repainted near gray
|
|
region = out[y : y + h, x : x + w]
|
|
assert abs(float(region.mean()) - 120) < 20
|
|
assert not np.array_equal(out, img)
|
|
|
|
def test_pixels_outside_box_untouched(self):
|
|
img, box = self._image_with_logo()
|
|
out = erase(img, boxes=[box], backend="cv2", dilate=0)
|
|
# a far corner must be identical
|
|
assert np.array_equal(img[:50, :50], out[:50, :50])
|
|
|
|
def test_no_boxes_returns_copy(self):
|
|
img = np.full((100, 100, 3), 50, np.uint8)
|
|
out = erase(img, boxes=[], backend="cv2")
|
|
assert np.array_equal(img, out)
|
|
|
|
def test_empty_mask_returns_copy(self):
|
|
img = np.full((100, 100, 3), 50, np.uint8)
|
|
out = erase(img, mask=np.zeros((100, 100), np.uint8), backend="cv2")
|
|
assert np.array_equal(img, out)
|
|
|
|
|
|
class TestNonBgrInputs:
|
|
"""cv2.inpaint rejects 4-channel BGRA and 2D-only entry points must work."""
|
|
|
|
def test_grayscale_2d_does_not_raise(self):
|
|
gray = np.full((100, 100), 120, np.uint8)
|
|
out = erase(gray, boxes=[(40, 40, 20, 20)], backend="cv2")
|
|
assert out.shape == gray.shape
|
|
|
|
def test_bgra_preserves_alpha_and_does_not_raise(self):
|
|
bgra = np.full((100, 100, 4), 120, np.uint8)
|
|
bgra[..., 3] = 200 # opaque-ish alpha plane
|
|
out = erase(bgra, boxes=[(40, 40, 20, 20)], backend="cv2", dilate=0)
|
|
assert out.shape == bgra.shape
|
|
# alpha plane is carried through unchanged
|
|
assert np.array_equal(out[..., 3], bgra[..., 3])
|
|
|
|
|
|
class TestBackendTable:
|
|
"""The fill-backend names are stated in several places; they must agree.
|
|
|
|
They are deliberately separate LITERALS rather than one derived list: deriving the
|
|
CLI choices or the registry's ``Backend`` from ``region_eraser`` would give
|
|
``watermark_registry`` (and therefore every ``--help`` and every metadata-only
|
|
``identify``) a module-level cv2 import. This test keeps the copies in sync instead.
|
|
"""
|
|
|
|
def test_registry_literal_matches_the_eraser_table(self):
|
|
import typing
|
|
|
|
from remove_ai_watermarks import region_eraser, watermark_registry
|
|
|
|
assert set(typing.get_args(watermark_registry.Backend)) == set(region_eraser.FILL_BACKENDS)
|
|
|
|
def test_executable_backends_are_the_table_minus_auto(self):
|
|
import typing
|
|
|
|
from remove_ai_watermarks import region_eraser
|
|
|
|
assert set(typing.get_args(region_eraser.Backend)) == set(region_eraser.FILL_BACKENDS) - {"auto"}
|
|
|
|
def test_learned_backends_name_real_module_attributes(self):
|
|
from remove_ai_watermarks import region_eraser
|
|
|
|
for name, row in region_eraser._LEARNED_BACKENDS.items():
|
|
assert name in region_eraser.FILL_BACKENDS
|
|
assert callable(getattr(region_eraser, row.available))
|
|
assert callable(getattr(region_eraser, row.erase))
|
|
|
|
def test_unknown_backend_degrades_to_cv2_instead_of_raising(self):
|
|
"""``erase`` is public: a library caller passing ``"auto"`` (or a typo) must get
|
|
the classical fill, not a KeyError."""
|
|
img = np.full((64, 64, 3), 100, np.uint8)
|
|
mask = np.zeros((64, 64), np.uint8)
|
|
mask[20:40, 20:40] = 255
|
|
assert erase(img, mask=mask, backend="auto").shape == img.shape # type: ignore[arg-type]
|
|
|
|
|
|
class TestLamaBackend:
|
|
def test_lama_raises_when_unavailable(self):
|
|
img = np.full((100, 100, 3), 50, np.uint8)
|
|
if lama_available():
|
|
pytest.skip("onnxruntime installed; cannot test the unavailable path")
|
|
with pytest.raises(RuntimeError, match="onnxruntime"):
|
|
erase(img, boxes=[(10, 10, 20, 20)], backend="lama")
|
|
|
|
|
|
class TestLamaChannelHandling:
|
|
"""erase_lama must accept grayscale (2D) and BGRA (4-channel) like erase_cv2.
|
|
|
|
The real ONNX model is never loaded -- the session is faked to an identity
|
|
inpaint, so this exercises only the channel promote/split wrapper (the fix for
|
|
LaMa crashing on grayscale and dropping alpha on BGRA).
|
|
"""
|
|
|
|
@pytest.fixture
|
|
def _fake_lama(self, monkeypatch: pytest.MonkeyPatch):
|
|
from remove_ai_watermarks import region_eraser
|
|
|
|
class _In:
|
|
def __init__(self, name: str, shape: list[int]):
|
|
self.name = name
|
|
self.shape = shape
|
|
|
|
class _FakeSession:
|
|
def get_inputs(self):
|
|
return [_In("image", [1, 3, 512, 512]), _In("mask", [1, 1, 512, 512])]
|
|
|
|
def run(self, _outputs, feeds):
|
|
# Identity inpaint: echo the image tensor (1,3,size,size) back.
|
|
return [feeds["image"]]
|
|
|
|
monkeypatch.setattr(region_eraser, "lama_available", lambda: True)
|
|
monkeypatch.setattr(region_eraser, "_get_lama_session", lambda: _FakeSession())
|
|
|
|
@pytest.mark.usefixtures("_fake_lama")
|
|
def test_grayscale_2d_does_not_raise(self):
|
|
gray = np.full((100, 100), 120, np.uint8)
|
|
out = erase(gray, boxes=[(40, 40, 20, 20)], backend="lama")
|
|
assert out.ndim == 2
|
|
assert out.shape == gray.shape
|
|
|
|
@pytest.mark.usefixtures("_fake_lama")
|
|
def test_bgra_preserves_alpha(self):
|
|
bgra = np.full((100, 100, 4), 120, np.uint8)
|
|
bgra[..., 3] = 200 # opaque-ish alpha plane
|
|
out = erase(bgra, boxes=[(40, 40, 20, 20)], backend="lama")
|
|
assert out.shape == bgra.shape
|
|
assert np.array_equal(out[..., 3], bgra[..., 3]) # alpha carried through unchanged
|
|
|
|
|
|
class TestMiganBackend:
|
|
def test_migan_raises_when_unavailable(self):
|
|
img = np.full((100, 100, 3), 50, np.uint8)
|
|
if migan_available():
|
|
pytest.skip("onnxruntime installed; cannot test the unavailable path")
|
|
with pytest.raises(RuntimeError, match="onnxruntime"):
|
|
erase(img, boxes=[(10, 10, 20, 20)], backend="migan")
|
|
|
|
|
|
class TestMiganWrapper:
|
|
"""erase_migan without the real model: fake session returns a solid-red field
|
|
and captures the fed mask. Exercises the mask-polarity inversion, masked-only
|
|
compositing, and grayscale/BGRA channel handling."""
|
|
|
|
captured: dict
|
|
|
|
@pytest.fixture
|
|
def _fake_migan(self, monkeypatch: pytest.MonkeyPatch):
|
|
from remove_ai_watermarks import region_eraser
|
|
|
|
self.captured = {}
|
|
|
|
class _In:
|
|
def __init__(self, name: str):
|
|
self.name = name
|
|
|
|
class _FakeSession:
|
|
def __init__(self, outer):
|
|
self.outer = outer
|
|
|
|
def get_inputs(self):
|
|
return [_In("image"), _In("mask")]
|
|
|
|
def run(self, _outputs, feeds):
|
|
self.outer.captured["mask"] = feeds["mask"]
|
|
self.outer.captured["image_shape"] = feeds["image"].shape
|
|
img = feeds["image"] # (1,3,H,W) RGB
|
|
red = np.zeros_like(img)
|
|
red[:, 0] = 255 # pure red in RGB
|
|
return [red]
|
|
|
|
monkeypatch.setattr(region_eraser, "migan_available", lambda: True)
|
|
monkeypatch.setattr(region_eraser, "_get_migan_session", lambda: _FakeSession(self))
|
|
|
|
@pytest.mark.usefixtures("_fake_migan")
|
|
def test_composites_only_masked_region_and_inverts_mask(self):
|
|
img = np.full((100, 100, 3), 120, np.uint8) # BGR
|
|
out = erase(img, boxes=[(40, 40, 20, 20)], backend="migan", dilate=0)
|
|
# inside the box -> red (BGR (0,0,255)); outside -> untouched
|
|
assert tuple(int(v) for v in out[50, 50]) == (0, 0, 255)
|
|
assert np.array_equal(out[:30, :30], img[:30, :30])
|
|
# mask fed to MI-GAN is inverted: 0 (hole) inside the box, 255 (known) outside
|
|
m = self.captured["mask"][0, 0]
|
|
assert m[50, 50] == 0
|
|
assert m[10, 10] == 255
|
|
|
|
@pytest.mark.usefixtures("_fake_migan")
|
|
def test_crops_around_mask_so_onnx_input_is_bounded(self):
|
|
# Large frame, small corner mark: the tensor fed to MI-GAN is the padded
|
|
# CROP (pad = max(256, 2*bbox)), not the full image -- this is what holds the
|
|
# ONNX working set roughly constant on big uploads instead of scaling with
|
|
# the image (the memory fix). Untouched pixels stay exact; the mark is filled.
|
|
img = np.full((2000, 3000, 3), 120, np.uint8)
|
|
out = erase(img, boxes=[(2900, 1900, 60, 60)], backend="migan", dilate=0)
|
|
assert out.shape == img.shape
|
|
_, _, fh, fw = self.captured["image_shape"]
|
|
assert fh < 700 # crop height, not the 2000px frame
|
|
assert fw < 700 # crop width, not the 3000px frame
|
|
assert tuple(int(v) for v in out[1930, 2930]) == (0, 0, 255) # mark -> red fill
|
|
assert np.array_equal(out[:100, :100], img[:100, :100]) # far corner untouched
|
|
|
|
@pytest.mark.usefixtures("_fake_migan")
|
|
def test_grayscale_2d_does_not_raise(self):
|
|
gray = np.full((100, 100), 120, np.uint8)
|
|
out = erase(gray, boxes=[(40, 40, 20, 20)], backend="migan", dilate=0)
|
|
assert out.ndim == 2
|
|
assert out.shape == gray.shape
|
|
|
|
@pytest.mark.usefixtures("_fake_migan")
|
|
def test_bgra_preserves_alpha(self):
|
|
bgra = np.full((100, 100, 4), 120, np.uint8)
|
|
bgra[..., 3] = 200
|
|
out = erase(bgra, boxes=[(40, 40, 20, 20)], backend="migan", dilate=0)
|
|
assert out.shape == bgra.shape
|
|
assert np.array_equal(out[..., 3], bgra[..., 3])
|