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.

我们提出了一种神经架构搜索 (NAS) 技术，以在最近提出的深度图像先验 (DIP) 下增强图像去噪、修复和超分辨率任务。我们表明，进化搜索可以自动优化 DIP 网络的编码器-解码器 (ED) 结构和元参数，在规范这些单个图像恢复任务之前，它充当特定于内容的内容。我们的二进制表示对非对称 ED 网络的设计空间进行编码，该网络通常会使用 500 人的人口规模在 10--20 代内收敛以产生特定于内容的 DIP。优化的架构不断改进经典 DIP 的视觉质量，以实现多样化摄影和艺术内容的范围。