PyNET-CA: Enhanced PyNET with Channel Attention for End-to-End Mobile Image Signal Processing
This work addresses mobile image signal processing for smartphone photography, but it is incremental as it builds on an existing model.
The authors tackled the problem of reconstructing RGB images from RAW data on mobile devices by proposing PyNET-CA, an enhanced deep learning model that improves upon the state-of-the-art PyNET with channel attention and a subpixel reconstruction module, achieving competitive results as demonstrated in the AIM 2020 challenge.
Reconstructing RGB image from RAW data obtained with a mobile device is related to a number of image signal processing (ISP) tasks, such as demosaicing, denoising, etc. Deep neural networks have shown promising results over hand-crafted ISP algorithms on solving these tasks separately, or even replacing the whole reconstruction process with one model. Here, we propose PyNET-CA, an end-to-end mobile ISP deep learning algorithm for RAW to RGB reconstruction. The model enhances PyNET, a recently proposed state-of-the-art model for mobile ISP, and improve its performance with channel attention and subpixel reconstruction module. We demonstrate the performance of the proposed method with comparative experiments and results from the AIM 2020 learned smartphone ISP challenge. The source code of our implementation is available at https://github.com/egyptdj/skyb-aim2020-public