Do any of these watermark removal systems support simple "training" on multiple images with identical watermarks? Having multiple example images with consistent watermarks should make removing watermarks much easier than trying to remove one with no context.
Honest question, is there even a legitimate use for this specific tech?
AnthonyMouse 7 hours ago [-]
Removing watermarks from works that have since fallen into the public domain, or were to begin with when a service debased it with their logo.
gs17 10 hours ago [-]
The legitimate uses feel kind of rare. Maybe there's some stock photo abandonware out there (questionable "legitimacy", but it's not so out there)? Maybe someone bought stock photos from a company that went bankrupt and never downloaded the non-watermarked version, and somehow that company's IP isn't accessible now? Feels like a stretch.
Upscaling old purchased images feels like a more common need.
IshKebab 9 hours ago [-]
Removing the annoying watermarks that some TV stations put in the corner of their shows...
efilife 7 hours ago [-]
removing the annoying "shot with x phone"
ipsum2 11 hours ago [-]
It's not illegal to remove watermarks from photos. Ethics is another thing.
djha-skin 10 hours ago [-]
Incorrect. Removing the watermark constitutes a derivative work. To distribute this work you need permission from the copyright owner to be legal. This you will almost certainly not get since the point of watermarks is to keep people from stealing copyrighted material.
cmeacham98 8 hours ago [-]
When in the process of removing the watermark do I distribute the work?
gs17 6 hours ago [-]
You're correct, making a derivative work isn't automatically "illegal". But what can you do with the de-watermarked image?
constantcrying 10 hours ago [-]
Their first example at https://www.clear.photo/en is absolutely terrible. I assume a showcase would show "good" results, but they display a complete failure.
- Incorrectly identifies areas for inpainting. You can see this with the figure, a lot of detail, not obscured by the watermark, is erased and then redrawn. This leads to a totally distorted look. The belt just disappears into nothing, the cloth just becomes a gradient, where a crisp line used to be.
- Low quality inpainting. Even the inpainting is done terribly. This looks like something done with some very simple diffusion based inpainting. Absolutely not state of the art.
not-chatgpt 10 hours ago [-]
What would be the state of the art?
GaggiX 10 hours ago [-]
Yeah their approach of using two different models to detect and then inpaint is very subliminal given that many watermarks are semi-transparent. They could have just trained a UNet with adversarial loss + LPIPS to do all the work and it would have worked much better already.
jelder 8 hours ago [-]
And some people call generative AI nothing but a copyright laundry…
speerer 11 hours ago [-]
This is technicaly impressive, but I wonder if this could be put to a use which is generally more constructive. Like maybe removing stains from scans or red eye from pictures.
I haven't found a tool that implements the techniques described in this Google paper from 8 years ago: https://watermark-cvpr17.github.io/
Upscaling old purchased images feels like a more common need.
- Incorrectly identifies areas for inpainting. You can see this with the figure, a lot of detail, not obscured by the watermark, is erased and then redrawn. This leads to a totally distorted look. The belt just disappears into nothing, the cloth just becomes a gradient, where a crisp line used to be.
- Low quality inpainting. Even the inpainting is done terribly. This looks like something done with some very simple diffusion based inpainting. Absolutely not state of the art.
How is this technical impressive? It fails at segmentation and it fails at inpainting.
I presume for a commercial product you would but a successful result front and center.