Weighted Dark Channel Dehazing

TL;DR

This paper introduces a weighted dark channel dehazing method that improves upon traditional dark channel approaches by controlling the local constant assumption with a novel weight map, leading to better dehazing quality and robustness.

Contribution

It proposes a new approach that separates dark pixels from the local assumption and uses a weight map to enhance dehazing accuracy, addressing limitations of prior dark channel methods.

Findings

Significant improvement in dehazing quality.

Robustness to initial transmission estimates.

Competitive processing speed.

Abstract

In dark channel based methods, local constant assumption is widely used to make the algorithms invertible. It inevitably introduces defects since the assumption can not perfectly avoid depth discontinuities and meanwhile cover enough pixels. Unfortunately, because of the limitation of the prior, which only confirms the existence of dark things but does not specify their locations or likelihood, no fidelity measurement is available in refinement thus the defects are either under-corrected or over-corrected. In this paper, we go deeper than the dark channel theory to overcome this problem. We split the concept of dark channel into dark pixels and local constant assumption, and then, control the problematic assumption based on a novel weight map. With such effort, our methods show significant improvement on quality and have competitive speed. In the last, we show that the method is highly robust to initial transmission estimates and can be ever-improved by providing better dark pixel locations.