iPhone 240fps Video Dataset for Various Model Training Tasks

High frame rate videos are recently used for training a variety of image processing tasks such as image/video deblurring and frame interpolation. Yet, the number of publicly available datasets with high frame rate videos are still limited. In this paper, we propose the iPhone 240fps dataset, a datas...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE International Conference on Consumer Electronics (ICCE) pp. 1 - 5
Main Authors Shimizu, Joi, Komatsu, Shion, Kobayashi, Satsuki, Sun, Heming, Katto, Jiro
Format Conference Proceeding
LanguageEnglish
Published IEEE 06.01.2023
Subjects
Consumer electronics
deblurring
deep learning
frame interpolation
high frame rate
Interpolation
Superresolution
Task analysis
Training
video super-resolution
Videos
Online AccessGet full text

Cover

More Information
Summary:High frame rate videos are recently used for training a variety of image processing tasks such as image/video deblurring and frame interpolation. Yet, the number of publicly available datasets with high frame rate videos are still limited. In this paper, we propose the iPhone 240fps dataset, a dataset which consists of real world 240fps videos. We conduct experiments with deblurring and frame interpolation models to show the effectiveness of this dataset. We also use this dataset to conduct experiments with a state-of-the-art video super-resolution model. We take advantage of the flexibility to change the frame rate of the dataset and test which fps is best suited for training the model. We believe this dataset can make contributions to future works in image and video processing. The dataset is publicly available on our cloud storage † † https://waseda.box.com/s/4ihxczdiythmeml38ndgsq4l1q90vnpp:
ISSN:2158-4001
DOI:10.1109/ICCE56470.2023.10043423