Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction

12/09/2021
by   Hyungjin Chung, et al.
0

Diffusion models have recently attained significant interest within the community owing to their strong performance as generative models. Furthermore, its application to inverse problems have demonstrated state-of-the-art performance. Unfortunately, diffusion models have a critical downside - they are inherently slow to sample from, needing few thousand steps of iteration to generate images from pure Gaussian noise. In this work, we show that starting from Gaussian noise is unnecessary. Instead, starting from a single forward diffusion with better initialization significantly reduces the number of sampling steps in the reverse conditional diffusion. This phenomenon is formally explained by the contraction theory of the stochastic difference equations like our conditional diffusion strategy - the alternating applications of reverse diffusion followed by a non-expansive data consistency step. The new sampling strategy, dubbed Come-Closer-Diffuse-Faster (CCDF), also reveals a new insight on how the existing feed-forward neural network approaches for inverse problems can be synergistically combined with the diffusion models. Experimental results with super-resolution, image inpainting, and compressed sensing MRI demonstrate that our method can achieve state-of-the-art reconstruction performance at significantly reduced sampling steps.

READ FULL TEXT

page 1

page 6

page 7

page 17

page 20

page 21

page 22

page 23

research
03/10/2023

Fast Diffusion Sampler for Inverse Problems by Geometric Decomposition

Diffusion models have shown exceptional performance in solving inverse p...
research
11/19/2022

Parallel Diffusion Models of Operator and Image for Blind Inverse Problems

Diffusion model-based inverse problem solvers have demonstrated state-of...
research
07/02/2023

Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models

We present the first framework to solve linear inverse problems leveragi...
research
09/29/2022

Diffusion Posterior Sampling for General Noisy Inverse Problems

Diffusion models have been recently studied as powerful generative inver...
research
02/27/2022

Conditional Simulation Using Diffusion Schrödinger Bridges

Denoising diffusion models have recently emerged as a powerful class of ...
research
06/02/2022

Improving Diffusion Models for Inverse Problems using Manifold Constraints

Recently, diffusion models have been used to solve various inverse probl...
research
05/31/2023

Direct Diffusion Bridge using Data Consistency for Inverse Problems

Diffusion model-based inverse problem solvers have shown impressive perf...

Please sign up or login with your details

Forgot password? Click here to reset