Deep Koalarization: Image Colorization using CNNs and Inception-ResNet-v2
Federico Baldassarre, Diego González Morín, Lucas Rodés-Guirao
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/baldassarreFe/deep-koalarizationOfficialIn papertf★ 0
- github.com/kkhosla96/cs231n-projectnone★ 0
- github.com/2023-MindSpore-4/Code7/tree/main/ssd_inception_v2mindspore★ 0
- github.com/ahemaesh/Deep-Image-Colorizationpytorch★ 0
- github.com/2023-MindSpore-1/ms-code-216/tree/main/resnetv2mindspore★ 0
- github.com/2023-MindSpore-1/ms-code-217/tree/main/ssd_inception_v2mindspore★ 0
- github.com/bluejurand/Photos-colorizationtf★ 0
- github.com/Ye11ow-Flash/ColorIttf★ 0
- github.com/Chirayushya/colorizationtf★ 0
- github.com/wusize/colorizationpytorch★ 0
Abstract
We review some of the most recent approaches to colorize gray-scale images using deep learning methods. Inspired by these, we propose a model which combines a deep Convolutional Neural Network trained from scratch with high-level features extracted from the Inception-ResNet-v2 pre-trained model. Thanks to its fully convolutional architecture, our encoder-decoder model can process images of any size and aspect ratio. Other than presenting the training results, we assess the "public acceptance" of the generated images by means of a user study. Finally, we present a carousel of applications on different types of images, such as historical photographs.