PVDD: A Practical Video Denoising Dataset with Real-World Dynamic Scenes

To facilitate video denoising research, we construct a compelling dataset, namely, "Practical Video Denoising Dataset" (PVDD), containing 200 noisy-clean dynamic video pairs in both sRGB and RAW format. Compared with existing datasets consisting of limited motion information, PVDD covers d...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-07
Main Authors: Xu, Xiaogang, Yu, Yitong, Jiang, Nianjuan, Lu, Jiangbo, Yu, Bei, Jia, Jiaya
Format: Article
Language:English
Subjects:
Datasets
Domains
Noise reduction
Poisson distribution
Synthesis
Video
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To facilitate video denoising research, we construct a compelling dataset, namely, "Practical Video Denoising Dataset" (PVDD), containing 200 noisy-clean dynamic video pairs in both sRGB and RAW format. Compared with existing datasets consisting of limited motion information, PVDD covers dynamic scenes with varying and natural motion. Different from datasets using primary Gaussian or Poisson distributions to synthesize noise in the sRGB domain, PVDD synthesizes realistic noise from the RAW domain with a physically meaningful sensor noise model followed by ISP processing. Moreover, based on this dataset, we propose a shuffle-based practical degradation model to enhance the performance of video denoising networks on real-world sRGB videos. Extensive experiments demonstrate that models trained on PVDD achieve superior denoising performance on many challenging real-world videos than on models trained on other existing datasets.
ISSN:2331-8422