Neural Architecture Search for Deep Image Prior

14 Jan 2020  ·  Kary Ho, Andrew Gilbert, Hailin Jin, John Collomosse ·

We present a neural architecture search (NAS) technique to enhance the performance of unsupervised image de-noising, in-painting and super-resolution under the recently proposed Deep Image Prior (DIP). We show that evolutionary search can automatically optimize the encoder-decoder (E-D) structure and meta-parameters of the DIP network, which serves as a content-specific prior to regularize these single image restoration tasks... Our binary representation encodes the design space for an asymmetric E-D network that typically converges to yield a content-specific DIP within 10-20 generations using a population size of 500. The optimized architectures consistently improve upon the visual quality of classical DIP for a diverse range of photographic and artistic content. read more

PDF Abstract

Datasets


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods