Image Enhancement using Generative Adversarial Networks

Abstract

Mobile Photography has been brought to a significantly new level in the last several years. The quality of images taken by the compact lenses of a smartphone have now appreciably increased. Now, even some of the low- end phones of the market spectrum are able to take exceedingly good photos in suitable availability of lighting, due to the advancement in numerous software methods for processing the images post capture. However, despite these tools, these cam- eras still fall behind the aesthetic capabilities of their DSLR counterparts. In the quest to achieve high quality images through a smartphone camera, various image semantics are inadvertently ignored leading to a less artistic image quality than a pro- fessional camera. Although numerous techniques for manual as well as computerized image en- hancement tasks do exist, they are generally only focused on brightness or contrast and other such global parameters of the image and does not go on to improve the content or texture of the image and neither do they take the various semantics of the image into account. Moreover, they are usually based on a predetermined set of rules that never considers the actual device specifics that is capturing the image — the smartphone camera. For our enhancement, we have endeavored to use a unique deep learning technique to transform lower quality images from a smartphone camera into DSLR-quality images. To enhance the image sharpness, we have used an error function that combines the three losses - the content, texture and color loss from the given image. By training on the large-scale DSLR Photo Enhancement Dataset, we have optimized the loss function using Generative Adversarial Networks. The end results produced after testing on a number of smartphone images yield enhanced quality images comparable to the DSLR images with an average SSIM score of approximately 0.95.