An Efficient Algorithm for Video Super-Resolution Based On a Sequential Model

TL;DR

This paper introduces a fast, convergent algorithm for video super-resolution that leverages a sequential model and sparsity priors to recover high-resolution videos from low-resolution inputs, demonstrating superior performance.

Contribution

It presents a novel optimization framework with provable convergence and linear complexity for high-dimensional, non-convex video super-resolution problems.

Findings

Algorithm shows good performance on video benchmarks.

Outperforms existing state-of-the-art methods.

Efficient handling of large-scale, non-convex problems.

Abstract

In this work, we propose a novel procedure for video super-resolution, that is the recovery of a sequence of high-resolution images from its low-resolution counterpart. Our approach is based on a "sequential" model (i.e., each high-resolution frame is supposed to be a displaced version of the preceding one) and considers the use of sparsity-enforcing priors. Both the recovery of the high-resolution images and the motion fields relating them is tackled. This leads to a large-dimensional, non-convex and non-smooth problem. We propose an algorithmic framework to address the latter. Our approach relies on fast gradient evaluation methods and modern optimization techniques for non-differentiable/non-convex problems. Unlike some other previous works, we show that there exists a provably-convergent method with a complexity linear in the problem dimensions. We assess the proposed optimization method on {several video benchmarks and emphasize its good performance with respect to the state of the art.}