Visual Attribute Transfer through Deep Image Analogy

TL;DR

This paper introduces Deep Image Analogy, a method that transfers visual attributes like style, color, and texture between images with different appearances but similar semantic content using deep features and dense correspondence.

Contribution

It presents a novel deep learning-based technique for semantic correspondence and attribute transfer across diverse images, extending the concept of image analogy with deep features.

Findings

Effective style and texture transfer demonstrated

Successful color and style swapping across image types

Versatile application to sketches, paintings, and photos

Abstract

We propose a new technique for visual attribute transfer across images that may have very different appearance but have perceptually similar semantic structure. By visual attribute transfer, we mean transfer of visual information (such as color, tone, texture, and style) from one image to another. For example, one image could be that of a painting or a sketch while the other is a photo of a real scene, and both depict the same type of scene. Our technique finds semantically-meaningful dense correspondences between two input images. To accomplish this, it adapts the notion of "image analogy" with features extracted from a Deep Convolutional Neutral Network for matching; we call our technique Deep Image Analogy. A coarse-to-fine strategy is used to compute the nearest-neighbor field for generating the results. We validate the effectiveness of our proposed method in a variety of cases, including style/texture transfer, color/style swap, sketch/painting to photo, and time lapse.