The paper was published by IEEE Transactions on Image Processing.
Abstract: Enhancement of non-uniformly illuminated images often suffers from over-enhancement and produces unnatural results. This paper presents a naturalness preserved enhancement method for non-uniformly illuminated images, using a priori multi-layer lightness statistics acquired from high-quality images (NPIE-MLLS). Our work makes three important contributions: designing a novel multi-layer image enhancement model; deriving the multi-layer lightness statistics of high-quality outdoor images, which are incorporated into the multi-layer enhancement model; and showing that the overall quality rating of enhanced images is consistent with a combination of contrast enhancement and naturalness preservation. Two separate human observer evaluation studies were conducted on naturalness preservation and overall image quality. The results showed the proposed method outperformed four compared state-of-the-art enhancement methods.
- High-quality image database-Download.
- Low-quality images and enhanced results-Download.
- Naturalness assessment code and results-Download.
- Naturalness enhancement code-Download.
- Demo for the computation of the average lightness, the average lightness range, and their standard error of the mean-Download.
We have been working to release more code and results. Should you have any question, please make a comment in the following. Or, you can send message to email@example.com. We will try to solve the problem as soon as possible.
In the following, we will present our answers to the questions from readers: