Paper Explained - DDPM - Diffusion Models Beat GANs on Image Synthesis (Full Video Analysis)

GANs have dominated the image generation space for the majority of the last decade. This paper shows for the first time, how a non-GAN model, a DDPM, can be improved to overtake GANs at standard evaluation metrics for image generation. The produced samples look amazing and other than GANs, the new model has a formal probabilistic foundation. Is there a future for GANs or are Diffusion Models going to overtake them for good?

0:00 - Intro & Overview
4:10 - Denoising Diffusion Probabilistic Models
11:30 - Formal derivation of the training loss
23:00 - Training in practice
27:55 - Learning the covariance
31:25 - Improving the noise schedule
33:35 - Reducing the loss gradient noise
40:35 - Classifier guidance
52:50 - Experimental Results

Paper (this): [2105.05233] Diffusion Models Beat GANs on Image Synthesis
Paper (previous): [2102.09672] Improved Denoising Diffusion Probabilistic Models