Abstract
•Representation and method for evolutionary neural architecture search of encoder-decoder architectures for Deep Image prior,•Leveraging a state-of-the-art perceptual metric to guide the optimization.•State of the art DIP results for inpainting, denoising, up-scaling, beating the hand-optimized DIP architectures proposed.•Demonstrated the content- style dependency of DIP architectures.
We present a neural architecture search (NAS) technique to enhance image denoising, inpainting, and super-resolution tasks 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.