Learning spatially varying regularisation parameters of low regularity for image reconstruction

The article reviews how spatially adaptive regularisation weight functions can be incorporated into variational image reconstruction models like Total Variation and Total Generalised Variation. It discusses the regularity properties of these weights—constant, continuous, or piecewise constant—and how they influence edge and detail preservation. The authors highlight recent hybrid methods that learn low‑regularity weights via deep neural networks, demonstrating their effectiveness in image denoising and MRI reconstruction.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.