Inverse problem

Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems

DDS enables fast sampling from the posterior without the need for heavy gradient computation in DIS.

Direct Diffusion Bridge for Inverse Problems with Data Consistency

We show that seemingly different direct diffusion bridges are equivalent, and that we can push the pareto frontier of the perception-distortion tradeoff with data consistency gradient guidance.

Improving 3D Imaging with Pre-Trained Perpendicular 2D Diffusion Models

TPDM improves 3D voxel generative modeling with 2D diffusion models. We show that 3D generative prior can be accurately represented as the product of two independent 2D diffusion priors that scale to both unconditional sampling and solving inverse problems.

Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models

We propose a method that can solve 3D inverse problems in the medical imaging domain using only the pre-trained 2D diffusion model augmented with the conventional model-based prior.

Diffusion Posterior Sampling for General Noisy Inverse Problems

Diffusion posterior sampling enables solving arbitrary noisy (e.g. Gaussian, Poisson) inverse problems that are both linear or non-linear.

Improving Diffusion Models for Inverse Problems using Manifold Constraints

Manifold constraint dramatically improves the performance of unsupervised inverse problem solving using diffusion models.