Watermark segmentation
github.com
Watermark segmentation
1–10 of 22 posts
Re: Watermark segmentation
#2This 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.
Re: Watermark segmentation
#3Honest question, is there even a legitimate use for this specific tech?
Re: Watermark segmentation
#4Do 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.
I haven't found a tool that implements the techniques described in this Google paper from 8 years ago: https://watermark-cvpr17.github.io/
Re: Watermark segmentation
#5Honest question, is there even a legitimate use for this specific tech?
It's not illegal to remove watermarks from photos. Ethics is another thing.
Re: Watermark segmentation
#6Their 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.
Re: Watermark segmentation
#7This 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.
Look at their first example on: https://www.clear.photo/en
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.
Re: Watermark segmentation
#8Their 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 g…
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.
Re: Watermark segmentation
#9Their 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 g…
What would be the state of the art?
Re: Watermark segmentation
#10Honest question, is there even a legitimate use for this specific tech?
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.