search

lthero-big / A-watermark-for-Diffusion-Models

This is an unofficial implementation of the Paper by Kejiang Chen et.al. on Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models
GNU General Public License v3.0
31 stars 2 forks source link

different crop result from paper #4

Open pokaaa opened 7 months ago

pokaaa commented 7 months ago

Different from the result reported in the paper of random crop, it turns out that the bit accuracy of crop with ratio 0.9 achieves about 0.6, and ratio 0.7 or less achieves about 0.5.

Did you also achieve this result?

I think this result might be reasonable because the whole latent is divided into chunks of 256 bits, and then voting is done on each position. However, the positions themselves may not correspond to the correct starting point.

Maybe for extraction we need to start from different points and choose the best result? I'm not sure if my analysis is correct.

lthero-big commented 6 months ago

I've reviewed the paper again and noticed that the bit accuracy rate of random crop is close to 1.0 when crop ratio is bigger than 0.5 . I think your analysis is reasonable , would you mind elaborating more about the solution cause I didn't understand it correctly.