A Comprehensive Method for Example-Based Color Transfer with Holistic–Local Balancing and Unit-Wise Riemannian Information Gradient Acceleration
Color transfer, an essential technique in image editing, has recently received significant attention. However, achieving a balance between holistic color style transfer and local detail refinement remains a challenging task. This paper proposes an innovative color transfer method, named BHL, which s...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/26/11/918 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850217286305054720 |
|---|---|
| author | Zeyu Wang Jialun Zhou Song Wang Ning Wang |
| author_facet | Zeyu Wang Jialun Zhou Song Wang Ning Wang |
| author_sort | Zeyu Wang |
| collection | DOAJ |
| description | Color transfer, an essential technique in image editing, has recently received significant attention. However, achieving a balance between holistic color style transfer and local detail refinement remains a challenging task. This paper proposes an innovative color transfer method, named BHL, which stands for Balanced consideration of both Holistic transformation and Local refinement. The BHL method employs a statistical framework to address the challenge of achieving a balance between holistic color transfer and the preservation of fine details during the color transfer process. Holistic color transformation is achieved using optimal transport theory within the generalized Gaussian modeling framework. The local refinement module adjusts color and texture details on a per-pixel basis using a Gaussian Mixture Model (GMM). To address the high computational complexity inherent in complex statistical modeling, a parameter estimation method called the unit-wise Riemannian information gradient (uRIG) method is introduced. The uRIG method significantly reduces the computational burden through the second-order acceleration effect of the Fisher information metric. Comprehensive experiments demonstrate that the BHL method outperforms state-of-the-art techniques in both visual quality and objective evaluation criteria, even under stringent time constraints. Remarkably, the BHL method processes high-resolution images in an average of 4.874 s, achieving the fastest processing time compared to the baselines. The BHL method represents a significant advancement in the field of color transfer, offering a balanced approach that combines holistic transformation and local refinement while maintaining efficiency and high visual quality. |
| format | Article |
| id | doaj-art-2efe1f189dd64cff9ee6426f718aea31 |
| institution | OA Journals |
| issn | 1099-4300 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj-art-2efe1f189dd64cff9ee6426f718aea312025-08-20T02:08:04ZengMDPI AGEntropy1099-43002024-10-01261191810.3390/e26110918A Comprehensive Method for Example-Based Color Transfer with Holistic–Local Balancing and Unit-Wise Riemannian Information Gradient AccelerationZeyu Wang0Jialun Zhou1Song Wang2Ning Wang3School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, ChinaColor transfer, an essential technique in image editing, has recently received significant attention. However, achieving a balance between holistic color style transfer and local detail refinement remains a challenging task. This paper proposes an innovative color transfer method, named BHL, which stands for Balanced consideration of both Holistic transformation and Local refinement. The BHL method employs a statistical framework to address the challenge of achieving a balance between holistic color transfer and the preservation of fine details during the color transfer process. Holistic color transformation is achieved using optimal transport theory within the generalized Gaussian modeling framework. The local refinement module adjusts color and texture details on a per-pixel basis using a Gaussian Mixture Model (GMM). To address the high computational complexity inherent in complex statistical modeling, a parameter estimation method called the unit-wise Riemannian information gradient (uRIG) method is introduced. The uRIG method significantly reduces the computational burden through the second-order acceleration effect of the Fisher information metric. Comprehensive experiments demonstrate that the BHL method outperforms state-of-the-art techniques in both visual quality and objective evaluation criteria, even under stringent time constraints. Remarkably, the BHL method processes high-resolution images in an average of 4.874 s, achieving the fastest processing time compared to the baselines. The BHL method represents a significant advancement in the field of color transfer, offering a balanced approach that combines holistic transformation and local refinement while maintaining efficiency and high visual quality.https://www.mdpi.com/1099-4300/26/11/918color transferstatistical modelingGMMoptimization on Riemannian manifold |
| spellingShingle | Zeyu Wang Jialun Zhou Song Wang Ning Wang A Comprehensive Method for Example-Based Color Transfer with Holistic–Local Balancing and Unit-Wise Riemannian Information Gradient Acceleration Entropy color transfer statistical modeling GMM optimization on Riemannian manifold |
| title | A Comprehensive Method for Example-Based Color Transfer with Holistic–Local Balancing and Unit-Wise Riemannian Information Gradient Acceleration |
| title_full | A Comprehensive Method for Example-Based Color Transfer with Holistic–Local Balancing and Unit-Wise Riemannian Information Gradient Acceleration |
| title_fullStr | A Comprehensive Method for Example-Based Color Transfer with Holistic–Local Balancing and Unit-Wise Riemannian Information Gradient Acceleration |
| title_full_unstemmed | A Comprehensive Method for Example-Based Color Transfer with Holistic–Local Balancing and Unit-Wise Riemannian Information Gradient Acceleration |
| title_short | A Comprehensive Method for Example-Based Color Transfer with Holistic–Local Balancing and Unit-Wise Riemannian Information Gradient Acceleration |
| title_sort | comprehensive method for example based color transfer with holistic local balancing and unit wise riemannian information gradient acceleration |
| topic | color transfer statistical modeling GMM optimization on Riemannian manifold |
| url | https://www.mdpi.com/1099-4300/26/11/918 |
| work_keys_str_mv | AT zeyuwang acomprehensivemethodforexamplebasedcolortransferwithholisticlocalbalancingandunitwiseriemannianinformationgradientacceleration AT jialunzhou acomprehensivemethodforexamplebasedcolortransferwithholisticlocalbalancingandunitwiseriemannianinformationgradientacceleration AT songwang acomprehensivemethodforexamplebasedcolortransferwithholisticlocalbalancingandunitwiseriemannianinformationgradientacceleration AT ningwang acomprehensivemethodforexamplebasedcolortransferwithholisticlocalbalancingandunitwiseriemannianinformationgradientacceleration AT zeyuwang comprehensivemethodforexamplebasedcolortransferwithholisticlocalbalancingandunitwiseriemannianinformationgradientacceleration AT jialunzhou comprehensivemethodforexamplebasedcolortransferwithholisticlocalbalancingandunitwiseriemannianinformationgradientacceleration AT songwang comprehensivemethodforexamplebasedcolortransferwithholisticlocalbalancingandunitwiseriemannianinformationgradientacceleration AT ningwang comprehensivemethodforexamplebasedcolortransferwithholisticlocalbalancingandunitwiseriemannianinformationgradientacceleration |