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
翻译:从使用移动设备获得的RAW数据中重建 RGB 图像的 RGB 图像与若干图像信号处理(ISP) 任务有关,例如演示、拆卸等。 深神经网络在单独解决这些任务,甚至用一个模型取代整个重建过程的手工制作 ISP算法方面,已经显示了有希望的结果。 我们在这里提议PyNET-CA,这是用于RAW到RGB重建的终端到终端移动 ISP深层次学习算法。 这个模型加强了PyNET,这是最近为移动 ISP提议的最先进的模型,并且用频道关注和子像素重建模块改进了它的性能。我们用AIM 2020 学会的智能手机 ISP挑战的比较实验和结果展示了拟议方法的性能。 我们的实施源代码可以在 https://github.com/egyptdj/sky-aim2020-public 上查阅。