azula.guidance.dps

Diffusion posterior sampling (DPS) internals.

References

Diffusion Posterior Sampling for General Noisy Inverse Problems (Chung et al., 2022)

https://arxiv.org/abs/2209.14687

Classes

DPSSampler

Creates a DPS sampler.

Descriptions

class azula.guidance.dps.DPSSampler(denoiser, y, A, zeta=1.0, **kwargs)

Creates a DPS sampler.

Parameters:

• denoiser (GaussianDenoiser) – A Gaussian denoiser.

• y (Tensor) – An observation \(y \sim \mathcal{N}(\mathcal{A}(x), \Sigma_y)\).

• A (Callable[[Tensor], Tensor]) – The forward operator \(\mathcal{A}\).

• zeta (float) – The guidance strength \(\zeta\).

• kwargs – Keyword arguments passed to azula.sample.Sampler.