omerbt
Why is averaging over overlapping regions necessary?
Why can't we just do non-overlapping generation without averaging? I presume you have tried and found that averaging gives better results. Is there any intuition or theory for that?
Can you suggest ways to to average and overlap masks? I went through the paper and the codes but I think I missed some important part.
Hello @yxchng, this is a great question that I had as well. The averaging between overlapping regions is necessary to create a coherent and smooth transition between the individual denoised patches. However, it turns out that you can also simply shift non-overlapping denoising windows through the timesteps such that borders in one timestep are corrected in the next which results in faster image generation, see our analysis here https://spotdiffusion.github.io/
