W-Net: Two-stage U-Net with misaligned data for raw-to-RGB mapping
This addresses the challenge of raw-to-RGB conversion for photography applications, but it is incremental as it builds on existing U-Net architectures.
The paper tackled the problem of mapping raw Bayer images to RGB images using the misaligned Zurich Raw-to-RGB dataset, achieving the highest PSNR and SSIM scores and second-best mean-opinion-score in the AIM 2019 challenge.
Recent research on learning a mapping between raw Bayer images and RGB images has progressed with the development of deep convolutional neural networks. A challenging data set namely the Zurich Raw-to-RGB data set (ZRR) has been released in the AIM 2019 raw-to-RGB mapping challenge. In ZRR, input raw and target RGB images are captured by two different cameras and thus not perfectly aligned. Moreover, camera metadata such as white balance gains and color correction matrix are not provided, which makes the challenge more difficult. In this paper, we explore an effective network structure and a loss function to address these issues. We exploit a two-stage U-Net architecture and also introduce a loss function that is less variant to alignment and more sensitive to color differences. In addition, we show an ensemble of networks trained with different loss functions can bring a significant performance gain. We demonstrate the superiority of our method by achieving the highest score in terms of both the peak signal-to-noise ratio and the structural similarity and obtaining the second-best mean-opinion-score in the challenge.