search

DPS2022 / diffusion-posterior-sampling

Official pytorch repository for "Diffusion Posterior Sampling for General Noisy Inverse Problems"
https://dps2022.github.io/diffusion-posterior-sampling-page/
425 stars 46 forks source link

Issue with random nonlinear blur kernel #7

Open z-fabian opened 1 year ago

z-fabian commented 1 year ago

It looks like every time the nonlinear blur operator is called, a new random blur kernel is generated. When calculating the guidance term, the kernel applied to the current posterior mean estimate and the kernel used to generate the measurement are different. Does this not cause an issue with data consistency? I think the kernels should be matched here. Thanks for your reply in advance!

Morefre commented 3 months ago

Same question, have you resolved it?