English

Color and Frequency Correction for Image Colorization

Computer Vision and Pattern Recognition 2025-10-28 v1

Abstract

The project has carried out the re-optimization of image coloring in accordance with the existing Autocolorization direction model DDColor. For the experiments on the existing weights of DDColor, we found that it has limitations in some frequency bands and the color cast problem caused by insufficient input dimension. We construct two optimization schemes and combine them, which achieves the performance improvement of indicators such as PSNR and SSIM of the images after DDColor.

Keywords

Cite

@article{arxiv.2510.23399,
  title  = {Color and Frequency Correction for Image Colorization},
  author = {Yun Kai Zhuang},
  journal= {arXiv preprint arXiv:2510.23399},
  year   = {2025}
}

Comments

7 pages, 5 tables

R2 v1 2026-07-01T07:07:48.478Z