Fast Color Constancy with Patch-wise Bright Pixels

TL;DR

The paper introduces a fast, learning-free color constancy algorithm called Patch-wise Bright Pixels (PBP) that efficiently estimates scene illumination by selecting bright pixels in image patches, outperforming existing methods in speed and accuracy.

Contribution

The novel PBP algorithm combines patch-wise analysis with brightness-based pixel selection, achieving rapid and accurate color constancy without machine learning.

Findings

PBP outperforms state-of-the-art learning-free methods.

PBP is hundreds of times faster than existing methods.

PBP effectively estimates scene illumination in real-time.

Abstract

In this paper, a learning-free color constancy algorithm called the Patch-wise Bright Pixels (PBP) is proposed. In this algorithm, an input image is first downsampled and then cut equally into a few patches. After that, according to the modified brightness of each patch, a proper fraction of brightest pixels in the patch is selected. Finally, Gray World (GW)-based methods are applied to the selected bright pixels to estimate the illuminant of the scene. Experiments on NUS $8$-Camera Dataset show that the PBP algorithm outperforms the state-of-the-art learning-free methods as well as a broad range of learning-based ones. In particular, PBP processes a $1080$p image within two milliseconds, which is hundreds of times faster than the existing learning-free ones. Our algorithm offers a potential solution to the full-screen smart phones whose screen-to-body ratio is $100$\%.