Abstract
We propose a novel end-to-end image colorization framework which integrates attention mechanism and a learnable adaptive normalization function. In contrast to previous colorization methods that directly generate the whole image, we believe that the color of the significant area determines the quality of the colorized image. The attention mechanism uses the attention map which is obtained by the auxiliary classifier to guide our framework to produce more subtle content and visually pleasing color in salient visual regions. Furthermore, we apply Adaptive Group Instance Normalization (AGIN) function to promote our framework to generate vivid colorized images flexibly, under the circumstance that we consider colorization as a particular style transfer task. Experiments show that our model is superior to previous the state-of-the-art models in coloring foreground objects.
Highlights
Colorization is a method of propagating color to a grayscale image, and the colorized image should be reasonable in content and visually comfortable
We propose a novel end-to-end image colorization framework which integrates attention mechanism and an adaptive normalization function
The decoder consists of two up-sampling convolutional layers with the stride size of one and four adaptive residual blocks which is equipped with Adaptive Group Instance Normalization (AGIN), unlike in the decoder where only instance normalization is used
Summary
Colorization is a method of propagating color to a grayscale image, and the colorized image should be reasonable in content and visually comfortable. We propose a novel end-to-end image colorization framework which integrates attention mechanism and an adaptive normalization function. Our framework colors image from grayscale domain with the guidance of the attention map which is obtained by the encoder feature map and importance weights acquired from the auxiliary classifier. Both generator and discriminator are affiliated with attention maps to focus on the importance salient region. We proposed a novel end-to-end framework for colorization with attention mechanism and AGIN which is a learnable normalization function. AGIN is a learnable normalization function which helps our framework generate reasonable color flexibly and freely without transforming the network
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have