[HN Gopher] Watermark segmentation
___________________________________________________________________
Watermark segmentation
Author : abriosi
Score : 21 points
Date : 2025-04-14 19:35 UTC (3 hours ago)
(HTM) web link (github.com)
(TXT) w3m dump (github.com)
| speerer wrote:
| 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.
| constantcrying wrote:
| 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.
| DavidVoid wrote:
| Honest question, is there even a _legitimate_ use for this
| specific tech?
| ipsum2 wrote:
| It's not illegal to remove watermarks from photos. Ethics is
| another thing.
| djha-skin wrote:
| 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 wrote:
| When in the process of removing the watermark do I
| distribute the work?
| gs17 wrote:
| 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 wrote:
| Removing the annoying watermarks that some TV stations put in
| the corner of their shows...
| xnx wrote:
| 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.
|
| I haven't found a tool that implements the techniques described
| in this Google paper from 8 years ago: https://watermark-
| cvpr17.github.io/
| constantcrying wrote:
| 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.
| GaggiX wrote:
| 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.
| not-chatgpt wrote:
| What would be the state of the art?
| James_K wrote:
| I'm surprised there isn't a readily available water-mark remover
| at this point. A synthetic training set for such a model could be
| created trivially.
| jelder wrote:
| And some people call generative AI nothing but a copyright
| laundry...
___________________________________________________________________
(page generated 2025-04-14 23:01 UTC)