[constantcrying]

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]

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]

What would be the state of the art?

[constantcrying]

State of the art is obviously a deep neural network trained for image generation/inpainting. Their inpainting mostly looks like a gradient smeared over the image. Current models can even create fine details and their problem, if anything, is being too detailed.