mirror of
https://github.com/wiltodelta/remove-ai-watermarks.git
synced 2026-08-09 23:50:40 +02:00
Add Hailuo, Kling, AVI, and FLV video coverage
This commit is contained in:
Victor Kuznetsov
+24
-16
@@ -134,17 +134,20 @@ remove-ai-watermarks video metadata input.mp4 --check
|
||||
remove-ai-watermarks video metadata input.mp4 --remove -o clean.mp4
|
||||
```
|
||||
|
||||
Supported containers are MP4, MOV, M4V, WebM, and MKV. The operation delegates
|
||||
to the same verified metadata scanner and stripper as the generic `metadata`
|
||||
command, so detection and removal stay in parity. Video and audio streams are
|
||||
not transcoded. For MP4 and MOV, this includes the native TC260 `AIGC` key and
|
||||
JSON value stored in `moov.udta.meta.keys/ilst`. The inspector seeks past a
|
||||
large `mdat` to find a tail `moov`; removal blanks the key and value in place so
|
||||
box sizes and media offsets do not move.
|
||||
Supported containers are MP4, MOV, M4V, WebM, MKV, AVI, and FLV. The operation
|
||||
delegates to the same verified metadata scanner and stripper as the generic
|
||||
`metadata` command, so detection and removal stay in parity. Video and audio
|
||||
streams are not transcoded. For MP4 and MOV, this includes the native TC260
|
||||
`AIGC` key and JSON value stored in `moov.udta.meta.keys/ilst`. The inspector
|
||||
seeks past a large `mdat` to find a tail `moov`; removal blanks the key and
|
||||
value in place so box sizes and media offsets do not move.
|
||||
|
||||
For MKV and WebM, the inspector reads the native TC260
|
||||
`Segment.Tags.Tag.SimpleTag` entry. Removal uses ffmpeg stream copying to
|
||||
discard container tags and chapters without transcoding the streams.
|
||||
AVI uses the normative `LIST/INFO/AIGC` chunk, while FLV uses the
|
||||
`script.onMetaData.AIGC` AMF0 string. Their bounded readers skip media payloads,
|
||||
and removal also uses ffmpeg stream copying.
|
||||
|
||||
When `-o` is omitted, the command writes `<source>_clean` with the same
|
||||
extension. It never overwrites the source, and it rejects an output with a
|
||||
@@ -192,22 +195,27 @@ remove-ai-watermarks video visible input.mp4 -o clean.mp4
|
||||
remove-ai-watermarks video visible veo.mp4 --mark veo -o veo_clean.mp4
|
||||
remove-ai-watermarks video visible seedance.mp4 --mark seedance -o seedance_clean.mp4
|
||||
remove-ai-watermarks video visible dola.mp4 --mark dola -o dola_clean.mp4
|
||||
remove-ai-watermarks video visible hailuo.mp4 --mark hailuo -o hailuo_clean.mp4
|
||||
remove-ai-watermarks video visible kling.mp4 --mark kling -o kling_clean.mp4
|
||||
```
|
||||
|
||||
The experimental command supports the moving Sora mascot and wordmark, two Veo
|
||||
corner variants, the Seedance boxed `AI` label, and the `Dola AI` text label.
|
||||
Sora searches the whole frame at multiple scales. The other detectors search
|
||||
bounded bottom-right regions with separate synthetic silhouettes. Every mark
|
||||
corner variants, the Seedance boxed `AI` label, the `Dola AI` text label, the
|
||||
composite `MINIMAX | hailuo AI` label, and the bottom-right Kling label. Sora
|
||||
searches the whole frame at multiple scales. The other detectors search bounded
|
||||
lower-frame regions with separate synthetic silhouettes. Kling additionally
|
||||
requires its bright low-saturation label near the frame edge. Every mark
|
||||
requires a spatially recurring candidate across adjacent frames. Fixed marks
|
||||
must also remain anchored instead of drifting with a scene object. Matching
|
||||
provider provenance may relax the visual score, but metadata alone never
|
||||
creates a detection. Clean API exports therefore remain untouched.
|
||||
provider provenance may relax the visual score only for registered
|
||||
provenance-aware marks; metadata alone never creates a detection.
|
||||
|
||||
The video stream is transcoded and the original audio stream is copied.
|
||||
Supported input and output containers are MP4, MOV, M4V, WebM, and MKV; the
|
||||
output extension must match the input. The default `cv2` backend is fast but can
|
||||
smear structured backgrounds. Select `--backend migan` or `--backend lama` for
|
||||
a learned fill, or `--backend auto` to choose the best installed backend.
|
||||
Supported input and output containers are MP4, MOV, M4V, WebM, MKV, AVI, and
|
||||
FLV; the output extension must match the input. The default `cv2` backend is
|
||||
fast but can smear structured backgrounds. Select `--backend migan` or
|
||||
`--backend lama` for a learned fill, or `--backend auto` to choose the best
|
||||
installed backend.
|
||||
|
||||
AI metadata is stripped from the encoded output by default. Use
|
||||
`--keep-metadata` to retain mapped container metadata. When no temporally stable
|
||||
|
||||
+18
-10
@@ -207,17 +207,21 @@ strip supported AI provenance metadata without transcoding streams.
|
||||
|
||||
`video visible` and `remove_video_visible` additionally support the moving
|
||||
Sora 2 mascot and wordmark, the current Veo four-point diamond, the legacy
|
||||
`Veo` text, the Seedance boxed `AI` label, and the fixed `Dola AI` text.
|
||||
Detection requires a recurring visual candidate across adjacent frames.
|
||||
Seedance, Dola, and Veo candidates must remain anchored rather than drifting
|
||||
with a scene object. Provider provenance can recover low-contrast runs only
|
||||
after visual evidence exists, so metadata alone does not erase a clean API
|
||||
export.
|
||||
`Veo` text, the Seedance boxed `AI` label, the fixed `Dola AI` text, the Hailuo
|
||||
MINIMAX/Hailuo composite label, and the bottom-right Kling label with its
|
||||
version suffix. Detection requires a recurring visual candidate across
|
||||
adjacent frames. Fixed-mark candidates must remain anchored rather than
|
||||
drifting with a scene object. Kling also requires a bright low-saturation
|
||||
candidate near the expected frame edge. Provider provenance can recover
|
||||
low-contrast runs only after visual evidence exists for the marks that define a
|
||||
provenance prior, so metadata alone does not erase a clean API export.
|
||||
Historical Sora Turbo exports use a small OpenAI swirl in the corner rather
|
||||
than the moving mascot-and-wordmark design; that earlier variant is not
|
||||
detected by the `sora` video mark. Other provider video labels are not
|
||||
supported yet. Google video SynthID has a candidate-producing VAE path, while
|
||||
other proprietary invisible video watermarks have no registered attack.
|
||||
detected by the `sora` video mark. Hailuo and Kling coverage is specific to the
|
||||
verified lower-edge layouts; a new provider layout needs a separate calibrated
|
||||
silhouette. Other provider video labels are not supported yet. Google video
|
||||
SynthID has a candidate-producing VAE path, while other proprietary invisible
|
||||
video watermarks have no registered attack.
|
||||
|
||||
Visible removal transcodes the video stream and copies audio. Its frame-local
|
||||
fill is not a motion-aware video inpainting model. OpenCV can leave a visible
|
||||
@@ -235,7 +239,11 @@ Native TC260 metadata in MP4/MOV is supported at its normative
|
||||
`moov.udta.meta.keys/ilst` placement, including non-faststart files whose
|
||||
`moov` follows a large media payload. MKV/WebM is supported at the normative
|
||||
`Segment.Tags.Tag.SimpleTag` placement and uses ffmpeg for stream-copy removal.
|
||||
The corresponding FLV and AVI native tags are not parsed yet.
|
||||
AVI is supported at `LIST/INFO/AIGC`, and FLV at
|
||||
`script.onMetaData.AIGC`; both use ffmpeg stream-copy removal. Stock ffmpeg can
|
||||
write and strip the FLV form, but writing the nonstandard AVI child for fixture
|
||||
generation requires dedicated muxer support, so the AVI reader is verified
|
||||
against an exact synthetic RIFF structure.
|
||||
|
||||
The current ISOBMFF stripper reads an MP4, MOV, or M4V container into memory
|
||||
before rewriting its metadata boxes. A streaming box copier is required before
|
||||
|
||||
+41
-21
@@ -115,6 +115,13 @@ only a `Segment.Tags.Tag.SimpleTag` pairing `TagName=AIGC` with a JSON
|
||||
`TagString` carrying a TC260 field. The existing ffmpeg stream-copy path removes
|
||||
those container tags without transcoding the encoded streams.
|
||||
|
||||
[`noai/riff.py`](../src/remove_ai_watermarks/noai/riff.py) and
|
||||
[`noai/flv.py`](../src/remove_ai_watermarks/noai/flv.py) implement the remaining
|
||||
normative TC260 video placements. The RIFF walker reads only AVI
|
||||
`LIST/INFO/AIGC` children. The FLV walker skips media tags and parses the AMF0
|
||||
`script.onMetaData.AIGC` string. Both require a recognized TC260 JSON field and
|
||||
use the verified ffmpeg stream-copy path for removal.
|
||||
|
||||
[`video_encoding.py`](../src/remove_ai_watermarks/video_encoding.py) owns the
|
||||
raw-BGR ffmpeg command and pipe lifecycle shared by visible removal and
|
||||
invisible regeneration. It centralizes container codecs, optional audio stream
|
||||
@@ -140,34 +147,44 @@ helpers to build a matched control and candidate grid, preventing research and
|
||||
shipped regeneration paths from drifting.
|
||||
|
||||
[`video_visible.py`](../src/remove_ai_watermarks/video_visible.py) implements
|
||||
the first pixel stages for Sora, Veo, Seedance, and Dola. The Sora detector
|
||||
searches a normalized frame with a fully synthetic mascot-and-text silhouette
|
||||
at several scales. The Veo detector uses separate synthetic silhouettes for the
|
||||
current four-point diamond and legacy `Veo` text. Seedance uses a synthetic
|
||||
rounded boxed-`AI` silhouette, while Dola uses an OpenCV-font `Dola AI`
|
||||
silhouette. All fixed-mark searches are bounded to the bottom-right area and
|
||||
calibrated independently. A strong relocated Veo diamond may bypass the known
|
||||
layout anchors, but weak free-corner matches never enter the temporal arbiter.
|
||||
the first pixel stages for Sora, Veo, Seedance, Dola, Hailuo, and Kling. The
|
||||
Sora detector searches a normalized frame with a fully synthetic
|
||||
mascot-and-text silhouette at several scales. The Veo detector uses separate
|
||||
synthetic silhouettes for the current four-point diamond and legacy `Veo`
|
||||
text. Seedance uses a synthetic rounded boxed-`AI` silhouette, while Dola uses
|
||||
an OpenCV-font `Dola AI` silhouette. Hailuo uses a synthetic waveform,
|
||||
MINIMAX/Hailuo text, separator, and ring. Kling combines synthetic font
|
||||
variants with a ring approximation of its swirl; the logo path rescues
|
||||
wordmarks whose version or font differs, while the edge and white-label gates
|
||||
reject recurring scene texture. All fixed-mark searches are bounded to the
|
||||
expected lower-frame area and calibrated independently. A strong relocated Veo
|
||||
diamond may bypass the known layout anchors, but weak free-corner matches never
|
||||
enter the temporal arbiter.
|
||||
|
||||
Every per-frame result is untrusted. The provider-specific stabilization
|
||||
wrappers share one recurrence implementation, while retaining separate visual
|
||||
floors and minimum-run policy. Provenance can relax a low-contrast run only
|
||||
after recurring visual evidence exists. Sora transition frames follow the
|
||||
nearest confirmed moving position only with Sora provenance. Veo, Seedance,
|
||||
and Dola additionally require candidates to remain anchored to the start of a
|
||||
run. This rejects slowly drifting scene details that still have high
|
||||
frame-to-frame overlap.
|
||||
Dola, Hailuo, and Kling additionally require candidates to remain anchored to
|
||||
the start of a run. This rejects slowly drifting scene details that still have
|
||||
high frame-to-frame overlap. Hailuo and Kling do not infer provenance from
|
||||
technical encoder tags; their confirmed public samples carried no provider
|
||||
metadata.
|
||||
|
||||
Removal runs in a second decode pass. Sora, legacy Veo text, Dola text, and the
|
||||
Seedance box use box masks. Seedance deliberately fills the complete localized
|
||||
box: a synthetic outline mask passed repeat detection but left part of the real
|
||||
translucent border visible during visual end-to-end review. The square Veo
|
||||
diamond uses a synthetic shape mask so transparent corners do not erase
|
||||
unrelated pixels. Every mask goes through the shared `watermark_registry.fill`
|
||||
backends. ffmpeg encodes the changed video stream and copies optional audio.
|
||||
The default OpenCV fill is the speed floor; structured backgrounds need MI-GAN
|
||||
or LaMa for better reconstruction. Invisible video stages must continue to
|
||||
reuse the image and metadata implementations rather than copying their logic.
|
||||
Removal runs in a second decode pass. Sora, legacy Veo text, Dola text,
|
||||
Seedance, Hailuo, and Kling use box masks. Seedance deliberately fills the
|
||||
complete localized box: a synthetic outline mask passed repeat detection but
|
||||
left part of the real translucent border visible during visual end-to-end
|
||||
review. Hailuo expands beyond the matched core to cover both provider icons.
|
||||
Kling expands around the wordmark or swirl to include the version and optional
|
||||
`PRO` suffix. The square Veo diamond uses a synthetic shape mask so transparent
|
||||
corners do not erase unrelated pixels. Every mask goes through the shared
|
||||
`watermark_registry.fill` backends. ffmpeg encodes the changed video stream and
|
||||
copies optional audio. The default OpenCV fill is the speed floor; structured
|
||||
backgrounds need MI-GAN or LaMa for better reconstruction. Invisible video
|
||||
stages must continue to reuse the image and metadata implementations rather
|
||||
than copying their logic.
|
||||
|
||||
The inherited ISOBMFF metadata path currently reads the complete container into
|
||||
memory; replacing that with a streaming box copier is a prerequisite for large
|
||||
@@ -205,6 +222,9 @@ Key contracts:
|
||||
`moov.udta.meta.keys/ilst` and blanked without changing box sizes.
|
||||
- Native MKV/WebM TC260 `AIGC` entries are read from
|
||||
`Segment.Tags.Tag.SimpleTag` and removed through the ffmpeg stream-copy path.
|
||||
- Native AVI and FLV TC260 entries are read from `LIST/INFO/AIGC` and
|
||||
`script.onMetaData.AIGC`, respectively, then removed through ffmpeg stream
|
||||
copying.
|
||||
- Supported non-ISOBMFF audio and video containers use ffmpeg stream copying.
|
||||
- The low-level remover is fail-safe and can copy an undecodable file through
|
||||
unchanged.
|
||||
|
||||
+21
-7
@@ -130,7 +130,8 @@ as proof that metadata was removed.
|
||||
|
||||
## Inspect and strip video metadata
|
||||
|
||||
The experimental high level video API supports MP4, MOV, M4V, WebM, and MKV:
|
||||
The experimental high level video API supports MP4, MOV, M4V, WebM, MKV, AVI,
|
||||
and FLV:
|
||||
|
||||
```python
|
||||
import remove_ai_watermarks as raiw
|
||||
@@ -152,7 +153,9 @@ inspection recognizes the native TC260 `AIGC` entry in
|
||||
`moov.udta.meta.keys/ilst`; its removal preserves container size and encoded
|
||||
stream bytes. MKV/WebM inspection recognizes the corresponding
|
||||
`Segment.Tags.Tag.SimpleTag` representation; its removal requires ffmpeg for a
|
||||
stream-copy remux.
|
||||
stream-copy remux. AVI inspection reads `LIST/INFO/AIGC`, and FLV inspection
|
||||
reads `script.onMetaData.AIGC`; both use the same verified ffmpeg stream-copy
|
||||
removal path.
|
||||
|
||||
## Generate a video SynthID candidate
|
||||
|
||||
@@ -211,16 +214,27 @@ dola_result = raiw.remove_video_visible(
|
||||
"dola_clean.mp4",
|
||||
mark="dola",
|
||||
)
|
||||
hailuo_result = raiw.remove_video_visible(
|
||||
"hailuo.mp4",
|
||||
"hailuo_clean.mp4",
|
||||
mark="hailuo",
|
||||
)
|
||||
kling_result = raiw.remove_video_visible(
|
||||
"kling.mp4",
|
||||
"kling_clean.mp4",
|
||||
mark="kling",
|
||||
)
|
||||
```
|
||||
|
||||
`remove_video_visible` scans the complete video before writing output. It
|
||||
combines synthetic multi-scale visual matching with temporal consistency, so an
|
||||
isolated lookalike in one frame is not enough to authorize inpainting. The
|
||||
supported `mark` values are `sora`, `veo`, `seedance`, and `dola`. The Veo
|
||||
detector recognizes the current four-point diamond and the legacy `Veo` text.
|
||||
Seedance recognizes the boxed `AI` label, while Dola recognizes its compact
|
||||
text label. Each variant has an independent synthetic silhouette and calibrated
|
||||
temporal policy.
|
||||
supported `mark` values are `sora`, `veo`, `seedance`, `dola`, `hailuo`, and
|
||||
`kling`. The Veo detector recognizes the current four-point diamond and the
|
||||
legacy `Veo` text. Seedance recognizes the boxed `AI` label, Dola recognizes
|
||||
its compact text label, Hailuo recognizes the composite MINIMAX/Hailuo label,
|
||||
and Kling recognizes its bottom-right logo, wordmark, and version suffix. Each
|
||||
variant has an independent synthetic silhouette and calibrated temporal policy.
|
||||
|
||||
The returned `VideoVisibleResult` records the total, detected, and removed frame
|
||||
counts plus any AI metadata that survived the output encode. The function
|
||||
|
||||
@@ -37,6 +37,8 @@ when you can select the affected area yourself.
|
||||
| `veo` | Current four-point diamond and legacy `Veo` text | Fixed bottom-right corner | Uses separate silhouettes and requires a recurring match; learned fill is preferable on structured backgrounds. |
|
||||
| `seedance` | Boxed `AI` label | Fixed bottom-right corner | Requires an anchored recurring match; the full localized box is filled because a thinner synthetic shape mask leaves the real translucent rim behind. |
|
||||
| `dola` | `Dola AI` text | Fixed bottom-right corner | Requires an anchored recurring match; ByteDance or BytePlus provenance can relax only an existing visual run. |
|
||||
| `hailuo` | `MINIMAX | hailuo AI` composite label | Fixed lower edge | Uses a synthetic waveform, text, separator, and ring silhouette; the complete recurring label box is filled. |
|
||||
| `kling` | Kling swirl, `KLING AI`, version, and optional `PRO` suffix | Fixed bottom-right edge | Combines a synthetic logo rescue with font variants, an edge gate, a white-label gate, and anchored temporal recurrence. |
|
||||
|
||||
Use `video visible` for this registry. It is separate from the image `visible`
|
||||
command because selection is made over a sequence rather than one raster.
|
||||
@@ -61,8 +63,9 @@ The inspection and stripping code handles signals in these groups:
|
||||
- IPTC AI disclosure fields;
|
||||
- PNG text chunks and embedded generation parameters;
|
||||
- China TC260 AIGC labels in supported image placements and the normative
|
||||
MP4/MOV `moov.udta.meta.keys/ilst` and MKV/WebM
|
||||
`Segment.Tags.Tag.SimpleTag` placements;
|
||||
MP4/MOV `moov.udta.meta.keys/ilst`, MKV/WebM
|
||||
`Segment.Tags.Tag.SimpleTag`, AVI `LIST/INFO/AIGC`, and FLV
|
||||
`script.onMetaData.AIGC` placements;
|
||||
- xAI and Grok EXIF signature fields;
|
||||
- Samsung AI editing markers;
|
||||
- Hugging Face job metadata;
|
||||
@@ -87,8 +90,8 @@ Metadata inspection and removal additionally have container paths for:
|
||||
|
||||
- JPEG XL metadata;
|
||||
- MP4, MOV, M4V, and M4A;
|
||||
- WebM, MKV, MKA, MP3, WAV, FLAC, OGG, OGA, Opus, and AAC when ffmpeg is
|
||||
available.
|
||||
- WebM, MKV, MKA, AVI, FLV, MP3, WAV, FLAC, OGG, OGA, Opus, and AAC when
|
||||
ffmpeg is available.
|
||||
|
||||
JPEG image metadata stripping removes targeted metadata segments without
|
||||
re-encoding the entropy coded image scan. PNG and WebP removal preserves pixel
|
||||
@@ -135,7 +138,8 @@ not a universal clean verdict.
|
||||
| Midjourney | None registered | No registered pixel decoder | EXIF, XMP, and IPTC signals |
|
||||
| ByteDance generators | Doubao and Jimeng marks | No registered pixel decoder | TC260 AIGC and supported C2PA signals |
|
||||
| Qwen | Qwen mark | No registered pixel decoder | TC260 AIGC |
|
||||
| Kling | Kling mark | No registered pixel decoder | TC260 AIGC |
|
||||
| Kling | Kling image and video marks | No registered pixel decoder | TC260 AIGC |
|
||||
| Hailuo / MiniMax video | Hailuo composite video label | No registered pixel decoder | TC260 AIGC where present |
|
||||
| Baidu | Baidu mark | No registered pixel decoder | TC260 AIGC |
|
||||
| LibLibAI | LibLibAI mark | No registered pixel decoder | TC260 AIGC |
|
||||
| RunningHub | RunningHub mark | No registered pixel decoder | TC260 AIGC |
|
||||
|
||||
@@ -45,6 +45,12 @@ Native MKV/WebM is a sixth serialization. TC260-PG-20257A stores
|
||||
`Segment.Tags.Tag.SimpleTag`. The bounded EBML reader skips cluster payloads;
|
||||
the existing ffmpeg stream-copy path removes the tags without transcoding.
|
||||
|
||||
The same [TC260 video guide](https://www.tc260.org.cn/portal/article/303/4061772dcf684d8a96f395a4298e9e53)
|
||||
defines two more native serializations. AVI stores an `AIGC` child in
|
||||
`LIST/INFO`; FLV stores an AMF0 `AIGC` string under `script.onMetaData`. The
|
||||
bounded RIFF and FLV readers validate the JSON field set and skip media
|
||||
payloads. Removal remuxes either container through ffmpeg with stream copy.
|
||||
|
||||
- **HuggingFace-hosted job (caught by `metadata.huggingface_job`, surfaced by `identify` as the `hf_job` signal, MEDIUM confidence):** HuggingFace Jobs / Spaces can stamp generated PNGs with an `hf-job-id` tEXt chunk holding the job UUID. It marks the *hosting job*, not a model, so it lifts an Unknown verdict to a tentative AI via `hf_only` but never overrides a hard metadata signal. `_HF_JOB_CAVEAT` states the limit. Removal drops the chunk through the PNG metadata whitelist.
|
||||
- **No detectable signal on some downloads:** Recraft exports and some hosted
|
||||
FLUX surfaces can arrive without a supported local signal. Midjourney samples
|
||||
@@ -56,8 +62,9 @@ the existing ffmpeg stream-copy path removes the tags without transcoding.
|
||||
- **Built in the dated batch:** soft-binding vendor detection, IPTC Photo
|
||||
Metadata AI-disclosure fields, C2PA detection and stripping for supported
|
||||
ISOBMFF video, the optional Adobe TrustMark decoder, and temporally stabilized
|
||||
visible Sora, Veo, Seedance, and Dola removal. Other visible video logos and
|
||||
proprietary audio-watermark detection remain outside the package.
|
||||
visible Sora, Veo, Seedance, Dola, Hailuo, and Kling removal. Other visible
|
||||
video logos and proprietary audio-watermark detection remain outside the
|
||||
package.
|
||||
Metadata stripping for supported audio containers is a separate implemented
|
||||
path.
|
||||
|
||||
@@ -101,6 +108,21 @@ every frame, then requires an anchored temporal run. This extra anchor check
|
||||
was necessary because a moving clean scene detail could retain enough adjacent
|
||||
overlap to pass a recurrence-only gate.
|
||||
|
||||
**Hailuo and Kling use larger fixed composite labels.** Verified Hailuo exports
|
||||
carry a lower-edge waveform, `MINIMAX`, separator, Hailuo ring, and
|
||||
`hailuo AI` text. Verified Kling exports carry a bottom-right swirl,
|
||||
`KLING AI`, a changing version suffix, and sometimes `PRO`. The detectors use
|
||||
only synthetic primitives and fonts. Hailuo expands the matched core to cover
|
||||
the complete composite. Kling combines a version-independent text core with a
|
||||
synthetic ring rescue, then requires the recurring candidate to reach the
|
||||
expected frame edge and contain enough bright low-saturation pixels. Those
|
||||
extra gates were added after clean Luma and PixVerse scene details passed shape
|
||||
and temporal recurrence alone. The generic
|
||||
[WatermarkRemover-AI](https://github.com/D-Ogi/WatermarkRemover-AI) project
|
||||
instead uses Florence-2 to identify arbitrary watermarks before LaMa
|
||||
inpainting. That is broader, but it carries a much heavier model and a less
|
||||
auditable detection boundary than the provider-specific synthetic path here.
|
||||
|
||||
**The faint-visible-mark precision/recall wall is fundamental, not a heuristic artifact.** The visible-watermark-detection literature has moved to LEARNED segmentation / object-detection (WDNet WACV'21 arXiv:2012.07616; SLBR ACM MM'21, open code+weights; the PRCV'18 large-scale detector; Su et al. survey 2025), but three verified findings bound what a learned detector actually buys: (1) a claim that a confidence threshold "cleanly separates" true from false matches even with a learned CNN front-end was **REFUTED** in verification (arXiv:1705.08593) -- the precision/recall wall persists even with learned features. (2) Learned detectors need a LARGE, pattern-diverse labeled dataset trained on synthetic composites (PRCV'18: 60k images / 80 watermark classes; CLWD: 60k / 160 marks), and off-distribution degradation is a documented real axis (models trained on limited-pattern LVW transfer worse; diversity of training patterns drives generalization). (3) Inference is cheap (WDNet ~8 ms at 256x256) -- the cost is the data pipeline, not runtime. Net: a learned detector shifts the frontier but does NOT remove the wall; for a SINGLE mark the cheapest next step is a small patch classifier (real-sparkle vs false-positive) on top of the existing NCC localizer, not a full segmentation model. SLBR is a ready baseline. The current NCC + false-positive gate (core-ring brightness margin + gradient-NCC crispness + white-core saturation) is a sound operating point, and the residual miss is the information-theoretic wall the literature confirms.
|
||||
|
||||
**Visible-mark landscape beyond the registry.** Meta stamps a visible "Imagined with AI" mark (bottom-LEFT, a small symbol) on its OWN Meta AI / "Imagine" output; for third-party images it relies on C2PA / IPTC, not a visible mark. Samsung Galaxy AI additionally uses a **four-star icon** variant in a corner alongside the localized text wordmark `samsung_engine` calibrates (only the Italian text variant is covered) -- the icon is a distinct, uncovered variant. Every source agrees visible + metadata marks are trivially removable (crop / screenshot, ~2 s), which is the tool's premise.
|
||||
|
||||
Reference in New Issue
Block a user