Confidence-aware Levenberg-Marquardt optimization for joint motion estimation and super-resolution

TL;DR

This paper presents a confidence-aware Levenberg-Marquardt optimization method for joint motion estimation and super-resolution, improving robustness and accuracy in reconstructing high-resolution images from low-resolution frames.

Contribution

It introduces a novel joint optimization framework with confidence-aware energy minimization and a tailored Levenberg-Marquardt scheme for simultaneous motion and image estimation.

Findings

Outperforms decoupled methods in experiments

Effective on simulated and real images

Enhances robustness of super-resolution process

Abstract

Motion estimation across low-resolution frames and the reconstruction of high-resolution images are two coupled subproblems of multi-frame super-resolution. This paper introduces a new joint optimization approach for motion estimation and image reconstruction to address this interdependence. Our method is formulated via non-linear least squares optimization and combines two principles of robust super-resolution. First, to enhance the robustness of the joint estimation, we propose a confidence-aware energy minimization framework augmented with sparse regularization. Second, we develop a tailor-made Levenberg-Marquardt iteration scheme to jointly estimate motion parameters and the high-resolution image along with the corresponding model confidence parameters. Our experiments on simulated and real images confirm that the proposed approach outperforms decoupled motion estimation and image reconstruction as well as related state-of-the-art joint estimation algorithms.