×

Colorization Transformer

swMATH ID: 42457
Software Authors: Manoj Kumar, Dirk Weissenborn, Nal Kalchbrenner
Description: Colorization Transformer. We present the Colorization Transformer, a novel approach for diverse high fidelity image colorization based on self-attention. Given a grayscale image, the colorization proceeds in three steps. We first use a conditional autoregressive transformer to produce a low resolution coarse coloring of the grayscale image. Our architecture adopts conditional transformer layers to effectively condition grayscale input. Two subsequent fully parallel networks upsample the coarse colored low resolution image into a finely colored high resolution image. Sampling from the Colorization Transformer produces diverse colorings whose fidelity outperforms the previous state-of-the-art on colorising ImageNet based on FID results and based on a human evaluation in a Mechanical Turk test. Remarkably, in more than 60
Homepage: https://arxiv.org/abs/2102.04432
Source Code:  https://github.com/google-research/google-research/tree/master/coltran
Dependencies: Python
Keywords: Colorization Transformer; Computer Vision; Pattern Recognition; arXiv_cs.CV; Artificial Intelligence; arXiv_cs.AI; Machine Learning; arXiv_cs.LG; Image colorization
Related Software: ImageNet; TransGAN; DeblurGAN; BERT; Python; ClusterFit; Flickr30K; PWC-Net; MeshLab; Face2Face; PoseCNN; NIMA; Make3D; EfficientNet; WSABIE; CIDEr; DISN; DVDnet; FaceNet; PointNet
Cited in: 1 Publication

Standard Articles

1 Publication describing the Software Year
Colorization Transformer
Manoj Kumar, Dirk Weissenborn, Nal Kalchbrenner
2021

Cited by 1 Author

1 Szeliski, Richard

Citations by Year