A color transfer algorithm between images based on two-stage convolutional neural network (CNN) is proposed. The first stage network is based on VGG19 architecture as the backbone. The reference image-based color transfer (RICT) model was used to extract the features of the reference image and the target image, so as to realize the color transfer between them. The second stage is based on progressive convolutional neural network (PCNN) as its backbone. The palette-based emotional color enhancement (PECE) model is adopted to enhance the emotional coloring of the resulting image by comparing the palette, emotional value and the proportion of each color of the reference image. Through five sets of experiments, it is proved that the visual effect processed by our model is obviously better than several main colorization methods in both subjective evaluation and objective data. It can be applied to various complex scenes, and in the near future, it can also be better applied to the fields of digital restoration of old image archives, medical image coloring, art restoration, remote sensing image enhancement, infrared image enhancement and other fields.

Style transfer is using a pair of content and style images to synthesize a stylized image which has both the structure of the content image and the style of style image. Existing optimization-based methods are limited in their performance. Some works using a feed-forward network allow arbitrary style transfer but cannot reflect the style. In this paper, we present a fast continuous structural similarity patch based arbitrary style transfer. Firstly, we introduce the structural similarity index (SSIM) to compute the similarity between all of the content and style patches for obtaining their similarity. Then a local style patch choosing procedure is applied to maximize the utilization of all style patches and make the swapped style patch continuous matching with respect to the spatial location of style at the same time. Finally, we apply an efficient trained feed-forward inverse network to obtain the final stylized image. We use more than 80,000 natural images and 120,000 style images to train that feed-forward inverse network. The results show that our method is able to transfer arbitrary style with consistency, and the result comparison stage is made to show the effectiveness and high-quality of our stylized images.

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.