Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures
This addresses the challenge of accurate color perception assessment for digital photography applications, particularly in scenarios with image misalignment, representing an incremental improvement over existing methods.
The paper tackles the problem of measuring color differences in misaligned photographic images by introducing a perceptual color difference measure based on multiscale sliced Wasserstein distances, which outperforms competing models in handling misalignment and shows promise for color transfer tasks.
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.