DeepCFL: Deep Contextual Features Learning from a Single Image

TL;DR

DeepCFL is a novel unsupervised framework that learns semantic features from a single image to perform diverse image synthesis and restoration tasks without training data dependence.

Contribution

It introduces DeepCFL, a single-image GAN framework that captures contextual semantic features for image synthesis and restoration, independent of training data.

Findings

Effective in outpainting, inpainting, and pixel restoration

Works with unaligned source and target images

Applicable to image resizing tasks

Abstract

Recently, there is a vast interest in developing image feature learning methods that are independent of the training data, such as deep image prior, InGAN, SinGAN, and DCIL. These methods are unsupervised and are used to perform low-level vision tasks such as image restoration, image editing, and image synthesis. In this work, we proposed a new training data-independent framework, called Deep Contextual Features Learning (DeepCFL), to perform image synthesis and image restoration based on the semantics of the input image. The contextual features are simply the high dimensional vectors representing the semantics of the given image. DeepCFL is a single image GAN framework that learns the distribution of the context vectors from the input image. We show the performance of contextual learning in various challenging scenarios: outpainting, inpainting, and restoration of randomly removed pixels. DeepCFL is applicable when the input source image and the generated target image are not aligned. We illustrate image synthesis using DeepCFL for the task of image resizing.