Summary of Grayscale Image Colorization with Gan and Cyclegan in Different Image Domain, by Chen Liang et al.
Grayscale Image Colorization with GAN and CycleGAN in Different Image Domain
by Chen Liang, Yunchen Sheng, Yichen Mo
First submitted to arxiv on: 21 Jan 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The research paper presents an investigation into automatic colorization of grayscale images using Generative Adversarial Networks (GANs) and CycleGAN models. Building on previous work that employed supervised methods, the authors reproduce a GAN-based coloring model and experiment with one of its variants. They also propose a new CycleGAN-based model and test it on various datasets. The results indicate that the proposed CycleGAN model excels in human-face and comic colorization tasks but struggles with diverse colorization. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Automatic colorization of grayscale images is now easier than ever! Researchers have been trying to figure out how to do this using special computer algorithms called Generative Adversarial Networks (GANs). They’ve already tried some ways, but they wanted to see if they could make it even better. In this paper, the authors test two new methods: one based on GANs and another based on something called CycleGAN. They try these methods out on different pictures and find that one of them is really good at coloring human faces and comics, but not so great at making the colors look different. |
Keywords
* Artificial intelligence * Gan * Supervised
