search

nihaomiao / CVPR23_LFDM

The pytorch implementation of our CVPR 2023 paper "Conditional Image-to-Video Generation with Latent Flow Diffusion Models"
BSD 2-Clause "Simplified" License
432 stars 43 forks source link

doubts about the model name in the code #34

Closed forever208 closed 8 months ago

forever208 commented 8 months ago

Hi @nihaomiao, thanks for open-sourcing the awesome work!

I have a few doubts about the model names in the code.

In the script run_natops.py, what do Generator, RegionPredictor and BGMotionPredictor mean and are used for? I am a bit confused because you denote the models as encoder, decoder and flow predictor in your paper. So, what are the correspondences of them?

nihaomiao commented 8 months ago

Hi, @forever208, our generator is based on the MRAA. You may refer to their paper and code for the role of these modules.