Saved in:
Bibliographic Details
Main Authors: He, Jiaqi, Wang, Zhihua, Wang, Leon, Liu, Tsein-I, Fang, Yuming, Sun, Qilin, Ma, Kede
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.10181
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929420219973632
author He, Jiaqi
Wang, Zhihua
Wang, Leon
Liu, Tsein-I
Fang, Yuming
Sun, Qilin
Ma, Kede
author_facet He, Jiaqi
Wang, Zhihua
Wang, Leon
Liu, Tsein-I
Fang, Yuming
Sun, Qilin
Ma, Kede
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_10181
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures
He, Jiaqi
Wang, Zhihua
Wang, Leon
Liu, Tsein-I
Fang, Yuming
Sun, Qilin
Ma, Kede
Computer Vision and Pattern Recognition
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.
title Multiscale Sliced Wasserstein Distances as Perceptual Color Difference Measures
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.10181