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?
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?