Example-based color transfer with Gaussian mixture modeling

@article{Gu2020ExamplebasedCT,
  title={Example-based color transfer with Gaussian mixture modeling},
  author={Chunzhi Gu and Xuequan Lu and Chao Zhang},
  journal={Pattern Recognit.},
  year={2020},
  volume={129},
  pages={108716}
}
[PDF] Semantic Reader
1 Citations
Background Citations
1
Methods Citations
1

Figures and Tables from this paper

One Citation

A Lightness-aware Nearest Neighbor Search Method for Exampled-based Color Transfer

  • Chunzhi GuChao Zhang
  • Computer Science
    2022 IEEE 11th Global Conference on Consumer Electronics (GCCE)
  • 2022
A lightness-aware nearest neighbor search procedure that allows users to select the lightness style of the transferred image to update the probability matrix in optimizing the parameters for the mixture model is proposed.

References

SHOWING 1-10 OF 68 REFERENCES

Corruptive Artifacts Suppression for Example-Based Color Transfer

This paper proposes a novel unified color transfer framework with corruptive artifacts suppression, which performs iterative probabilistic color mapping with self-learning filtering scheme and multiscale detail manipulation scheme in minimizing the normalized Kullback-Leibler distance.

Optimal Transportation for Example-Guided Color Transfer

The main strength of the method comes from using optimal transportation to map a pair of meaningful color palettes, and regularizing this mapping through thin plate splines, and it is shown that additional visual or semantic constraints can be seamlessly incorporated to obtain a consistent color mapping.

Soft Color Segmentation and Its Applications

An automatic approach to soft color segmentation is proposed, which produces soft color segments with an appropriate amount of overlapping and transparency essential to synthesizing natural images for a wide range of image-based applications and is shown to converge to a good optimal solution.

Deep color transfer using histogram analogy

A deep neural network is proposed that leverages color histogram analogy for color transfer, and this network utilizes the analogy between the source and reference histograms to modulate the color of the source image with abstract color features of the reference image.

Color Transfer Using Probabilistic Moving Least Squares

This paper introduces a new color transfer method using a scattered point interpolation scheme using moving least squares and strengthens it with a probabilistic modeling of the color transfer in the 3D color space to deal with mis-alignments and noise.

Filter Style Transfer between Photos

To the best of the knowledge, FST is the first style transfer method that can transfer custom filter effects between FHD image under 2ms on a mobile device without any textual context loss.

Robust Image-to-Image Color Transfer Using Optimal Inlier Maximization

  • Magnus Oskarsson
  • Computer Science
    2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2021
This paper presents a feature-based method, that robustly fits color transforms to data containing gross outliers, based on an optimal inlier maximization algorithm that maximizes the number of inliers in polynomial time.

Recoding Color Transfer as A Color Homography

A color-homography-based color transfer decomposition is proposed which encodes color transfer as a combination of chromaticity shift and shading adjustment and is shown to be a global shading curve by which the same shading homography can be applied elsewhere.

TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations

This paper proposes TransFill, a multi-homography transformed fusion method to fill the hole by referring to another source image that shares scene contents with the target image, and generalizes to user-provided image pairs.

Deep exemplar-based colorization

This work proposes the first deep learning approach for exemplar-based local colorization, which performs robustly and generalizes well even when using reference images that are unrelated to the input grayscale image.
...