AIM 2019 Challenge on RAW to RGB Mapping: Methods and Results

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 th...

Full description

Saved in:
Bibliographic Details
Main Authors: Ignatov, Andrey, Timofte, Radu, Ko, Sung-Jea, Kim, Seung-Wook, Uhm, Kwang-Hyun, Ji, Seo-Won, Cho, Sung-Jin, Hong, Jun-Pyo, Mei, Kangfu, Li, Juncheng, Zhang, Jiajie, Wu, Haoyu, Li, Jie, Huang, Rui, Haris, Muhammad, Shakhnarovich, Greg, Ukita, Norimichi, Zhao, Yuzhi, Po, Lai-Man, Zhang, Tiantian, Liao, Zongbang, Shi, Xiang, Zhang, Yujia, Ou, Weifeng, Xian, Pengfei, Xiong, Jingjing, Zhou, Chang, Yu, Wing Yin, Yubin, Yubin, Hou, Bingxin, Park, Bumjun, Yu, Songhyun, Kim, Sangmin, Jeong, Jechang
Format: Conference Proceeding
Language:English
Subjects:
AIM
AIM2019
Cameras
Challenge
Computer Vision
Deep Learning
Image color analysis
Image enhancement
Image Manipulation
Image resolution
Mobile Cameras
RAW to RGB
Runtime
Smartphones
Training
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2473-9944
DOI:10.1109/ICCVW.2019.00443