Raw Image Demoiréing Dataset
- Citation Author(s):
-
Huanjing Yue (Tianjin University)Yijia Cheng (Tianjin University)Yan MaoCong CaoJingyu Yang (Tianjin University)
- Submitted by:
- Yijia Cheng
- Last updated:
- DOI:
- 10.21227/vkam-v640
- Data Format:
747 views
- Categories:
Abstract
We provide ground truth images and moiré images in raw domain and sRGB domain respectively, which are placed in four folders gt_RAW_npz, gt_RGB, moire_RAW_npz and moire_RGB. The ground truth raw image is actually pseudo ground truth. The users can regenerate them by utilizing other RGB to raw inversing algorithms. Our raw domain data is stored in npz format, including black level corrected data, black level value, white level value and white balance value.
Instructions:
This dataset is constructed to learn the demoiriéng model via supervised learning. Please read our paper "Recaptured Screen Image Demoiréing in Raw Domain" published in IEEE Trans. on Multimedia for more details about the dataset construction and usage.
Funding Agency
National Natural Science Foundation of China
Grant Number
62072331
In reply to Our dataset is a benchmark by Yijia Cheng
666666666
for low-light enchance research