Towards Architecture-Agnostic Untrained Network Priors for Image Reconstruction with Frequency Regularization

arXiv:2312.09988v2 Announce Type: replace-cross
Abstract: Untrained networks inspired by deep image prior have shown promising capabilities in recovering a high-quality image from noisy or partial measurements, without requiring training data. Their success has been widely attributed to the spectral bias acting as an implicit regularization induced by suitable network architectures. However, applications of such network-based priors often entail superfluous architectural decisions, overfitting risks, and slow optimization, all of which hinder their practicality. In this work, we propose efficient, architecture-agnostic methods …

abstract acting architecture arxiv bias capabilities cs.cv data eess.iv image network networks prior quality regularization success training training data type