Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Paper typo: wrong equation in Background section for decoding process #66

Open
gh-BumsooKim opened this issue Jan 14, 2024 · 0 comments

Comments

@gh-BumsooKim
Copy link

gh-BumsooKim commented Jan 14, 2024

Thank you for researching excellent image-to-video synthesis work and sharing the code publicly.

I found that wrong equation in not only arXiv paper (https://arxiv.org/pdf/2304.06025.pdf) but also ICCV2023 paper (https://openaccess.thecvf.com/content/ICCV2023/papers/Karras_DreamPose_Fashion_Video_Synthesis_with_Stable_Diffusion_ICCV_2023_paper.pdf).

In Background section, I think this equation (between Eq.(1) and Eq.(2)) might be wrong :

image

I think it should be $x^\prime = \mathcal{D}(z^\prime)$ (x' = D(z'))
Because the variable which will be decoded from latent via decoder was encoded by VAE encoder, notating as z'.
This equation is same in arXiv version and ICCV publishing version.

I believe that correct equation (but I request you must confirm my new suggestion above) don't give a confusion for other researchers. Thank you.

@gh-BumsooKim gh-BumsooKim changed the title Paper typo: wrong equation in Background section for $L_{DM}$ Paper typo: wrong equation in Background section for decoding process Jan 14, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant