Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing
- URL: http://arxiv.org/abs/2407.01521v1
- Date: Mon, 1 Jul 2024 17:59:23 GMT
- Title: Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing
- Authors: Bingliang Zhang, Wenda Chu, Julius Berner, Chenlin Meng, Anima Anandkumar, Yang Song,
- Abstract summary: We propose a new method called Decoupled Annealing Posterior Sampling (DAPS) that relies on a novel noise annealing process.
DAPS significantly improves sample quality and stability across multiple image restoration tasks.
For example, we achieve a PSNR of 30.72dB on the FFHQ 256 dataset for phase retrieval, which is an improvement of 9.12dB compared to existing methods.
- Score: 84.97865583302244
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Diffusion models have recently achieved success in solving Bayesian inverse problems with learned data priors. Current methods build on top of the diffusion sampling process, where each denoising step makes small modifications to samples from the previous step. However, this process struggles to correct errors from earlier sampling steps, leading to worse performance in complicated nonlinear inverse problems, such as phase retrieval. To address this challenge, we propose a new method called Decoupled Annealing Posterior Sampling (DAPS) that relies on a novel noise annealing process. Specifically, we decouple consecutive steps in a diffusion sampling trajectory, allowing them to vary considerably from one another while ensuring their time-marginals anneal to the true posterior as we reduce noise levels. This approach enables the exploration of a larger solution space, improving the success rate for accurate reconstructions. We demonstrate that DAPS significantly improves sample quality and stability across multiple image restoration tasks, particularly in complicated nonlinear inverse problems. For example, we achieve a PSNR of 30.72dB on the FFHQ 256 dataset for phase retrieval, which is an improvement of 9.12dB compared to existing methods.
Related papers
- Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems [12.482127049881026]
We propose a novel approach to solve inverse problems with a diffusion prior from an amortized variational inference perspective.
Our amortized inference learns a function that directly maps measurements to the implicit posterior distributions of corresponding clean data, enabling a single-step posterior sampling even for unseen measurements.
arXiv Detail & Related papers (2024-07-23T02:14:18Z) - Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors [21.51814794909746]
In this work, we take a different approach to define a set of intermediate and simpler posterior sampling problems, resulting in a lower approximation error compared to previous methods.
We empirically demonstrate the reconstruction capability of our method for general linear inverse problems using synthetic examples and various image restoration tasks.
arXiv Detail & Related papers (2024-03-18T01:47:24Z) - Decoupled Data Consistency with Diffusion Purification for Image Restoration [15.043002968696978]
We propose a novel diffusion-based image restoration solver that addresses issues by decoupling the reverse process from the data consistency steps.
Our approach demonstrates versatility, making it highly adaptable for efficient problem-solving in latent space.
The efficacy of our approach is validated through comprehensive experiments across various image restoration tasks, including image denoising, deblurring, inpainting, and super-resolution.
arXiv Detail & Related papers (2024-03-10T00:47:05Z) - ResShift: Efficient Diffusion Model for Image Super-resolution by
Residual Shifting [70.83632337581034]
Diffusion-based image super-resolution (SR) methods are mainly limited by the low inference speed.
We propose a novel and efficient diffusion model for SR that significantly reduces the number of diffusion steps.
Our method constructs a Markov chain that transfers between the high-resolution image and the low-resolution image by shifting the residual.
arXiv Detail & Related papers (2023-07-23T15:10:02Z) - Parallel Sampling of Diffusion Models [76.3124029406809]
Diffusion models are powerful generative models but suffer from slow sampling.
We present ParaDiGMS, a novel method to accelerate the sampling of pretrained diffusion models by denoising multiple steps in parallel.
arXiv Detail & Related papers (2023-05-25T17:59:42Z) - A Variational Perspective on Solving Inverse Problems with Diffusion
Models [101.831766524264]
Inverse tasks can be formulated as inferring a posterior distribution over data.
This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable.
We propose a variational approach that by design seeks to approximate the true posterior distribution.
arXiv Detail & Related papers (2023-05-07T23:00:47Z) - Diffusion Model Based Posterior Sampling for Noisy Linear Inverse
Problems [17.49551570305112]
We propose an unsupervised sampling approach called diffusion model based posterior sampling (DMPS) to reconstruct the unknown signal from noisy linear measurements.
Specifically, using one diffusion model (DM) as an implicit prior, the fundamental difficulty in performing posterior sampling is that the noise-perturbed likelihood score, i.e., gradient of an annealed likelihood function, is intractable.
Extensive experiments are conducted on a variety of noisy linear inverse problems such as noisy super-resolution, denoising, deblurring, and colorization.
arXiv Detail & Related papers (2022-11-20T01:09:49Z) - Diffusion Posterior Sampling for General Noisy Inverse Problems [50.873313752797124]
We extend diffusion solvers to handle noisy (non)linear inverse problems via approximation of the posterior sampling.
Our method demonstrates that diffusion models can incorporate various measurement noise statistics.
arXiv Detail & Related papers (2022-09-29T11:12:27Z) - Improving Diffusion Models for Inverse Problems using Manifold Constraints [55.91148172752894]
We show that current solvers throw the sample path off the data manifold, and hence the error accumulates.
To address this, we propose an additional correction term inspired by the manifold constraint.
We show that our method is superior to the previous methods both theoretically and empirically.
arXiv Detail & Related papers (2022-06-02T09:06:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.