Efficient Bayesian Computational Imaging with a Surrogate Score-Based
Prior
- URL: http://arxiv.org/abs/2309.01949v1
- Date: Tue, 5 Sep 2023 04:55:10 GMT
- Title: Efficient Bayesian Computational Imaging with a Surrogate Score-Based
Prior
- Authors: Berthy T. Feng, Katherine L. Bouman
- Abstract summary: We propose a surrogate function for efficient use of score-based priors for inverse imaging.
Our work establishes a practical path forward for using score-based diffusion models as general-purpose priors for imaging.
- Score: 8.453791747558673
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose a surrogate function for efficient use of score-based priors for
Bayesian inverse imaging. Recent work turned score-based diffusion models into
probabilistic priors for solving ill-posed imaging problems by appealing to an
ODE-based log-probability function. However, evaluating this function is
computationally inefficient and inhibits posterior estimation of
high-dimensional images. Our proposed surrogate prior is based on the evidence
lower-bound of a score-based diffusion model. We demonstrate the surrogate
prior on variational inference for efficient approximate posterior sampling of
large images. Compared to the exact prior in previous work, our surrogate prior
accelerates optimization of the variational image distribution by at least two
orders of magnitude. We also find that our principled approach achieves
higher-fidelity images than non-Bayesian baselines that involve
hyperparameter-tuning at inference. Our work establishes a practical path
forward for using score-based diffusion models as general-purpose priors for
imaging.
Related papers
- Bayesian Conditioned Diffusion Models for Inverse Problems [11.67269909384503]
Diffusion models excel in many image reconstruction tasks that involve inverse problems based on a forward measurement operator.
We propose a novel Bayesian conditioning technique for diffusion models, BCDM, based on score-functions associated with the conditional distribution of desired images.
We show state-of-the-art performance in image dealiasing, deblurring, super-resolution, and inpainting with the proposed technique.
arXiv Detail & Related papers (2024-06-14T07:13:03Z) - Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction [31.503662384666274]
In science and engineering, the goal is to infer an unknown image from a small number of measurements collected from a known forward model describing certain imaging modality.
Motivated Score-based diffusion models, due to its empirical success, have emerged as an impressive candidate of an exemplary prior in image reconstruction.
arXiv Detail & Related papers (2024-03-25T15:58:26Z) - Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases [76.9127853906115]
Bridging the gap between diffusion models and human preferences is crucial for their integration into practical generative.
We propose Temporal Diffusion Policy Optimization with critic active neuron Reset (TDPO-R), a policy gradient algorithm that exploits the temporal inductive bias of diffusion models.
Empirical results demonstrate the superior efficacy of our methods in mitigating reward overoptimization.
arXiv Detail & Related papers (2024-02-13T15:55:41Z) - Exploiting Diffusion Prior for Generalizable Dense Prediction [85.4563592053464]
Recent advanced Text-to-Image (T2I) diffusion models are sometimes too imaginative for existing off-the-shelf dense predictors to estimate.
We introduce DMP, a pipeline utilizing pre-trained T2I models as a prior for dense prediction tasks.
Despite limited-domain training data, the approach yields faithful estimations for arbitrary images, surpassing existing state-of-the-art algorithms.
arXiv Detail & Related papers (2023-11-30T18:59:44Z) - Poisson-Gaussian Holographic Phase Retrieval with Score-based Image
Prior [19.231581775644617]
We propose a new algorithm called "AWFS" that uses the accelerated Wirtinger flow (AWF) with a score function as generative prior.
We calculate the gradient of the log-likelihood function for PR and determine the Lipschitz constant.
We provide theoretical analysis that establishes a critical-point convergence guarantee for the proposed algorithm.
arXiv Detail & Related papers (2023-05-12T18:08:47Z) - Score-Based Diffusion Models as Principled Priors for Inverse Imaging [46.19536250098105]
We propose turning score-based diffusion models into principled image priors.
We show how to sample from resulting posteriors by using this probability function for variational inference.
arXiv Detail & Related papers (2023-04-23T21:05:59Z) - Posterior samples of source galaxies in strong gravitational lenses with
score-based priors [107.52670032376555]
We use a score-based model to encode the prior for the inference of undistorted images of background galaxies.
We show how the balance between the likelihood and the prior meet our expectations in an experiment with out-of-distribution data.
arXiv Detail & Related papers (2022-11-07T19:00:42Z) - Posterior temperature optimized Bayesian models for inverse problems in
medical imaging [59.82184400837329]
We present an unsupervised Bayesian approach to inverse problems in medical imaging using mean-field variational inference with a fully tempered posterior.
We show that an optimized posterior temperature leads to improved accuracy and uncertainty estimation.
Our source code is publicly available at calibrated.com/Cardio-AI/mfvi-dip-mia.
arXiv Detail & Related papers (2022-02-02T12:16:33Z) - Regularization via deep generative models: an analysis point of view [8.818465117061205]
This paper proposes a new way of regularizing an inverse problem in imaging (e.g., deblurring or inpainting) by means of a deep generative neural network.
In many cases our technique achieves a clear improvement of the performance and seems to be more robust.
arXiv Detail & Related papers (2021-01-21T15:04:57Z) - A Flexible Framework for Designing Trainable Priors with Adaptive
Smoothing and Game Encoding [57.1077544780653]
We introduce a general framework for designing and training neural network layers whose forward passes can be interpreted as solving non-smooth convex optimization problems.
We focus on convex games, solved by local agents represented by the nodes of a graph and interacting through regularization functions.
This approach is appealing for solving imaging problems, as it allows the use of classical image priors within deep models that are trainable end to end.
arXiv Detail & Related papers (2020-06-26T08:34:54Z)
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.