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
Hi, I am interested in the performance of using 3d CNN without casual for VAE training, and corresponding results of generation. As I understand, the propose of Casual3dCNN is for autoregressive model of stage two in MagViT. Since our stage two is still diffusion, is there any consideration of using Casual3dCNN?
The text was updated successfully, but these errors were encountered:
Sutongtong233
changed the title
Have you
The performance gap between using vanilla 3dVAE and Casual3dCNN
Apr 15, 2024
We are currently just inflating 2DVAE to 3DVAE and replacing conv3d with causalconv3d. this already supports simultaneous training of images and videos.
Hi, I am interested in the performance of using 3d CNN without casual for VAE training, and corresponding results of generation. As I understand, the propose of Casual3dCNN is for autoregressive model of stage two in MagViT. Since our stage two is still diffusion, is there any consideration of using Casual3dCNN?
The text was updated successfully, but these errors were encountered: