Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures

TL;DR

This paper introduces a new perceptual color difference measure based on multiscale sliced Wasserstein distance, effectively handling misaligned images and aligning with human color perception, without requiring training.

Contribution

It proposes a novel, training-free color difference metric that captures perceptual organization and outperforms existing methods on misaligned photographic images.

Findings

Performs favorably in assessing color differences in photographic images.

Surpasses competing models in the presence of image misalignment.

Functions as a metric and shows promise as a loss function for color transfer.

Abstract

Contemporary color difference (CD) measures for photographic images typically operate by comparing co-located pixels, patches in a ``perceptually uniform'' color space, or features in a learned latent space. Consequently, these measures inadequately capture the human color perception of misaligned image pairs, which are prevalent in digital photography (e.g., the same scene captured by different smartphones). In this paper, we describe a perceptual CD measure based on the multiscale sliced Wasserstein distance, which facilitates efficient comparisons between non-local patches of similar color and structure. This aligns with the modern understanding of color perception, where color and structure are inextricably interdependent as a unitary process of perceptual organization. Meanwhile, our method is easy to implement and training-free. Experimental results indicate that our CD measure performs favorably in assessing CDs in photographic images, and consistently surpasses competing models in the presence of image misalignment. Additionally, we empirically verify that our measure functions as a metric in the mathematical sense, and show its promise as a loss function for image and video color transfer tasks. The code is available at https://github.com/real-hjq/MS-SWD.