Online Adaptive Image Reconstruction (OnAIR) Using Dictionary Models
This work addresses the need for efficient, real-time image reconstruction in applications such as medical imaging and video processing, though it is incremental as it builds on existing dictionary learning methods.
The paper tackles the problem of reconstructing dynamic image sequences from limited or corrupted measurements by proposing an online adaptive framework that simultaneously estimates a dictionary and images from streaming data, demonstrating effectiveness in tasks like video inpainting and dynamic MRI reconstruction from very limited measurements.
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.