You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In Background section, I think this equation (between Eq.(1) and Eq.(2)) might be wrong :
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.
The text was updated successfully, but these errors were encountered:
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
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 :
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.
The text was updated successfully, but these errors were encountered: