Color and Frequency Correction for Image Colorization
By: Yun Kai Zhuang
Potential Business Impact:
Makes old photos look colorful and clear again.
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.
Similar Papers
Automatic Image Colorization with Convolutional Neural Networks and Generative Adversarial Networks
CV and Pattern Recognition
Makes old black and white photos colorful again.
Automatic Image Colorization with Convolutional Neural Networks and Generative Adversarial Networks
CV and Pattern Recognition
Makes old black and white photos colorful again.
Prompt-based Consistent Video Colorization
CV and Pattern Recognition
Makes old black and white movies colorful automatically.