DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks
This work addresses the quality gap for smartphone users by enabling DSLR-like photos on mobile devices, though it is incremental as it builds on existing deep learning techniques.
The authors tackled the problem of improving smartphone photo quality to match DSLR standards by developing an end-to-end deep learning approach that translates ordinary photos into DSLR-quality images, achieving results comparable to DSLR-taken photos in quantitative and qualitative assessments.
Despite a rapid rise in the quality of built-in smartphone cameras, their physical limitations - small sensor size, compact lenses and the lack of specific hardware, - impede them to achieve the quality results of DSLR cameras. In this work we present an end-to-end deep learning approach that bridges this gap by translating ordinary photos into DSLR-quality images. We propose learning the translation function using a residual convolutional neural network that improves both color rendition and image sharpness. Since the standard mean squared loss is not well suited for measuring perceptual image quality, we introduce a composite perceptual error function that combines content, color and texture losses. The first two losses are defined analytically, while the texture loss is learned in an adversarial fashion. We also present DPED, a large-scale dataset that consists of real photos captured from three different phones and one high-end reflex camera. Our quantitative and qualitative assessments reveal that the enhanced image quality is comparable to that of DSLR-taken photos, while the methodology is generalized to any type of digital camera.