Online Adaptive Image Reconstruction (OnAIR) Using Dictionary Models

TL;DR

This paper introduces an online adaptive image reconstruction framework that models spatiotemporal patches as sparse in a dictionary, enabling efficient, sequential estimation of images and dictionaries from streaming measurements, useful in various inverse problems.

Contribution

It proposes a novel online algorithm for adaptive reconstruction of dynamic images using dictionary models, with constraints for efficiency and robustness, suitable for streaming data scenarios.

Findings

Effective in video reconstruction and inpainting from noisy, subsampled data

Demonstrates robustness in dynamic MRI reconstruction with limited measurements

Memory-efficient updates for dictionaries, images, and sparse coefficients

Abstract

Sparsity and low-rank models have been popular for reconstructing images and videos from limited or corrupted measurements. Dictionary or transform learning methods are useful in applications such as denoising, inpainting, and medical image reconstruction. This paper proposes a framework for online (or time-sequential) adaptive reconstruction of dynamic image sequences from linear (typically undersampled) measurements. We model the spatiotemporal patches of the underlying dynamic image sequence as sparse in a dictionary, and we simultaneously estimate the dictionary and the images sequentially from streaming measurements. Multiple constraints on the adapted dictionary are also considered such as a unitary matrix, or low-rank dictionary atoms that provide additional efficiency or robustness. The proposed online algorithms are memory efficient and involve simple updates of the dictionary atoms, sparse coefficients, and images. Numerical experiments demonstrate the usefulness of the proposed methods in inverse problems such as video reconstruction or inpainting from noisy, subsampled pixels, and dynamic magnetic resonance image reconstruction from very limited measurements.