AIM 2019 Challenge on RAW to RGB Mapping: Methods and Results
- 1 October 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3584-3590
Abstract
This paper reviews the first AIM challenge on mapping camera RAW to RGB images with the focus on proposed solutions and results. The participating teams were solving a real-world photo enhancement problem, where the goal was to map the original low-quality RAW images from the Huawei P20 device to the same photos captured with the Canon 5D DSLR camera. The considered problem embraced a number of computer vision subtasks, such as image demosaicing, denoising, gamma correction, image resolution and sharpness enhancement, etc. The target metric used in this challenge combined fidelity scores (PSNR and SSIM) with solutions' perceptual results measured in a user study. The proposed solutions significantly improved baseline results, defining the state-of-the-art for RAW to RGB image restoration.Keywords
This publication has 9 references indexed in Scilit:
- A Brief Review of Image Denoising Algorithms and Beyond2019
- Saliency Map-Aided Generative Adversarial Network for RAW to RGB Mapping2019
- W-Net: Two-Stage U-Net With Misaligned Data for Raw-to-RGB Mapping2019
- Perception-Preserving Convolutional Networks for Image Enhancement on Smartphones2019
- Fast Perceptual Image Enhancement2019
- Residual Dense Network for Image Super-Resolution2018
- NTIRE 2018 Challenge on Single Image Super-Resolution: Methods and Results2018
- Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs2018
- DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks2017