Barycenters of Natural Images -- Constrained Wasserstein Barycenters for Image Morphing

TL;DR

This paper introduces a constrained Wasserstein barycenter method for image morphing that ensures smooth, minimal, and realistic transitions by incorporating image priors, demonstrated with sparse priors and GANs.

Contribution

It proposes a novel constrained Wasserstein barycenter approach for image morphing that enforces image priors to produce more natural transitions.

Findings

The method produces smooth and realistic image transitions.

Incorporating priors reduces unnatural artifacts.

Demonstrated effectiveness with sparse priors and GANs.

Abstract

Image interpolation, or image morphing, refers to a visual transition between two (or more) input images. For such a transition to look visually appealing, its desirable properties are (i) to be smooth; (ii) to apply the minimal required change in the image; and (iii) to seem "real", avoiding unnatural artifacts in each image in the transition. To obtain a smooth and straightforward transition, one may adopt the well-known Wasserstein Barycenter Problem (WBP). While this approach guarantees minimal changes under the Wasserstein metric, the resulting images might seem unnatural. In this work, we propose a novel approach for image morphing that possesses all three desired properties. To this end, we define a constrained variant of the WBP that enforces the intermediate images to satisfy an image prior. We describe an algorithm that solves this problem and demonstrate it using the sparse prior and generative adversarial networks.