A Convex Approach for Image Hallucination

TL;DR

This paper introduces a convex optimization method for image hallucination that leverages aligned images and a face image database to produce high-resolution outputs with state-of-the-art quality.

Contribution

It formulates a convex primal optimization problem for image hallucination, providing a globally optimal solution and a fast converging primal-dual algorithm, improving over non-convex models.

Findings

Achieves state-of-the-art results in image hallucination.

Uses a convex approach for guaranteed global optimality.

Incorporates high-frequency details from face image database.

Abstract

In this paper we propose a global convex approach for image hallucination. Altering the idea of classical multi image super resolution (SU) systems to single image SU, we incorporate aligned images to hallucinate the output. Our work is based on the paper of Tappen et al. where they use a non-convex model for image hallucination. In comparison we formulate a convex primal optimization problem and derive a fast converging primal-dual algorithm with a global optimal solution. We use a database with face images to incorporate high-frequency details to the high-resolution output. We show that we can achieve state-of-the-art results by using a convex approach.