Rank-One Prior: Toward Real-Time Scene Recovery

TL;DR

This paper introduces a real-time scene recovery method that uses a rank-one transmission prior and an intensity projection strategy to enhance images degraded by weather conditions like sandstorms, underwater, and haze.

Contribution

It proposes a novel real-time light correction technique based on a rank-one prior, enabling efficient and robust scene recovery under various adverse conditions.

Findings

Outperforms state-of-the-art methods in efficiency and robustness

Estimates transmission with $O(N)$ complexity for real-time processing

Effective in diverse weather and imaging scenarios

Abstract

Scene recovery is a fundamental imaging task for several practical applications, e.g., video surveillance and autonomous vehicles, etc. To improve visual quality under different weather/imaging conditions, we propose a real-time light correction method to recover the degraded scenes in the cases of sandstorms, underwater, and haze. The heart of our work is that we propose an intensity projection strategy to estimate the transmission. This strategy is motivated by a straightforward rank-one transmission prior. The complexity of transmission estimation is $O(N)$ where $N$ is the size of the single image. Then we can recover the scene in real-time. Comprehensive experiments on different types of weather/imaging conditions illustrate that our method outperforms competitively several state-of-the-art imaging methods in terms of efficiency and robustness.