Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing
- URL: http://arxiv.org/abs/2407.01521v2
- Date: Wed, 18 Dec 2024 00:26:39 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)
DAPS relies on a novel noise annealing process.
We demonstrate that DAPS significantly improves sample quality and stability across multiple image restoration tasks.
- Score: 84.97865583302244
- License:
- 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.
Related papers
- Improving Decoupled Posterior Sampling for Inverse Problems using Data Consistency Constraint [13.285652967956652]
We propose Guided Decoupled Posterior Sampling (GDPS) to solve inverse problems.
We extend our method to latent diffusion models and Tweedie's formula.
GDPS achieves state-of-the-art performance, improving accuracy over existing methods.
arXiv Detail & Related papers (2024-12-01T03:57:21Z) - Enhancing Diffusion Posterior Sampling for Inverse Problems by Integrating Crafted Measurements [45.70011319850862]
Diffusion models have emerged as a powerful foundation model for visual generation.
Current posterior sampling based methods take the measurement into the posterior sampling to infer the distribution of the target data.
We show that high-frequency information can be prematurely introduced during the early stages, which could induce larger posterior estimate errors.
We propose a novel diffusion posterior sampling method DPS-CM, which incorporates a Crafted Measurement.
arXiv Detail & Related papers (2024-11-15T00:06:57Z) - Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors [21.0128625037708]
We present an innovative framework, divide-and-conquer posterior sampling.
It reduces the approximation error associated with current techniques without the need for retraining.
We demonstrate the versatility and effectiveness of our approach for a wide range of Bayesian inverse problems.
arXiv Detail & Related papers (2024-03-18T01:47:24Z) - 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 [14.809545109705256]
This paper presents a fast and effective solution by proposing a simple closed-form approximation to the likelihood score.
For both diffusion and flow-based models, extensive experiments are conducted on various noisy linear inverse problems.
Our method demonstrates highly competitive or even better reconstruction performances while being significantly faster than all the baseline methods.
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.