Bayesian Physics-Informed Neural Networks for Inverse Problems (BPINN-IP): Application in Infrared Image Processing

TL;DR

This paper introduces BPINN-IP, a Bayesian physics-informed neural network framework that enhances inverse problem solving by integrating physical laws, prior knowledge, and uncertainty quantification, demonstrated on infrared image processing tasks.

Contribution

It extends classical PINNs by incorporating Bayesian inference, enabling uncertainty quantification and a unified approach for inverse problems involving complex physics.

Findings

Effective in infrared image deconvolution and super-resolution

Handles noisy and limited data through Bayesian modeling

Demonstrates superior performance on simulated and real data

Abstract

Inverse problems arise across scientific and engineering domains, where the goal is to infer hidden parameters or physical fields from indirect and noisy observations. Classical approaches, such as variational regularization and Bayesian inference, provide well established theoretical foundations for handling ill posedness. However, these methods often become computationally restrictive in high dimensional settings or when the forward model is governed by complex physics. Physics Informed Neural Networks (PINNs) have recently emerged as a promising framework for solving inverse problems by embedding physical laws directly into the training process of neural networks. In this paper, we introduce a new perspective on the Bayesian Physics Informed Neural Network (BPINN) framework, extending classical PINNs by explicitly incorporating training data generation, modeling and measurement uncertainties through Bayesian prior modeling and doing inference with the posterior laws. Also, as we focus on the inverse problems, we call this method BPINN-IP, and we show that the standard PINN formulation naturally appears as its special case corresponding to the Maximum A Posteriori (MAP) estimate. This unified formulation allows simultaneous exploitation of physical constraints, prior knowledge, and data-driven inference, while enabling uncertainty quantification through posterior distributions. To demonstrate the effectiveness of the proposed framework, we consider inverse problems arising in infrared image processing, including deconvolution and super-resolution, and present results on both simulated and real industrial data.