DIFAR: Deep Image Formation and Retouching

11/29/2019 ∙ by Sean Moran, et al. ∙ 1

We present a novel neural network architecture for the image signal processing (ISP) pipeline. In a camera system, the ISP is a critical component that forms a high quality RGB image from RAW camera sensor data. Typical ISP pipelines sequentially apply a complex set of traditional image processing modules, such as demosaicing, denoising, tone mapping, etc. We introduce a new deep network that replaces all these modules, dubbed Deep Image Formation And Retouching (DIFAR). DIFAR introduces a multi-scale context-aware pixel-level block for local denoising/demosaicing operations and a retouching block for global refinement of image colour, luminance and saturation. DIFAR can also be trained for RGB to RGB image enhancement. DIFAR is parameter-efficient and outperforms recently proposed deep learning approaches in both objective and perceptual metrics, setting new state-of-the-art performance on multiple datasets including Samsung S7 and MIT-Adobe 5k.



There are no comments yet.


page 16

page 17

page 18

page 19

page 20

page 21

page 22

page 23

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.