4DLFVD: A 4D Light Field Video Dataset

Citation Author(s):
Xinjue
Hu
University of Ottawa / Beijing University of Posts and Telecommunication
Chenchen
Wang
Beijing University of Posts and Telecommunication
Yuxuan
Pan
Beijing University of Posts and Telecommunication
Yunming
Liu
Beijing University of Posts and Telecommunication
Yumei
Wang
Beijing University of Posts and Telecommunication
Yu
Liu
Beijing University of Posts and Telecommunication
Lin
Zhang
Beijing Information Science & Technology University / Beijing University of Posts and Telecommunication
Shervin
Shirmohammadi
University of Ottawa
Submitted by:
Xinjue Hu
Last updated:
Wed, 09/08/2021 - 13:18
DOI:
10.21227/hz0t-8482
Data Format:
Links:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

We present a 4D Light Field (LF) video dataset collected by the camera matrix, to be used for designing and testing algorithms and systems for LF video coding and processing. For collecting these videos, a 10x10 LF capture matrix composed of 100 cameras is designed and implemented, and the resolution of each camera is 1920x1056. The videos are taken in real and varying illumination conditions. The dataset contains a total of nine groups of LF videos, of which eight groups are collected with a fixed camera matrix position and a fixed orientation. The last group was collected by rotating around an outdoor specific target. Each group of LF videos consists of 100 video streams, which are encoded by H.265. Both static scenes (indoor potted plants and furniture, etc.) and dynamic scenes (roadside vehicles and pedestrians, etc.) are included, which can increase the diversity of our dataset. As a benchmark, we present the results of a depth estimation method designed by ourselves, and show that our dataset can be used for further processing and applications, such as objection detection and 3D modeling. The revised stone_tablet sequences have also been provided in a new zip file.

The dataset has been accepted by MMSys'21 Open Dataset and Software Track:

Xinjue Hu, Chenchen Wang, Yuxuan Pan, Yunming Liu, Yumei Wang, YuLiu, Lin Zhang, and Shervin Shirmohammadi. 2021. 4DLFVD: A 4D LightField Video Dataset. In12th ACM Multimedia Systems Conference (MMSys’21) (MMSys 21), September 28-October 1, 2021, Istanbul, Turkey.ACM, NewYork, NY, USA, 6 pages. https://doi.org/10.1145/3458305.34784501

Instructions: 

The stream data of all LF videos are stored under the directory LF_video_data, and each video contains 100 stream files. The stream files are in 1920 x 1056 24 frames per second MP4 format without audio. There are 100 mat files in the Calibration_mat directory, which store all camera parameters of 100 lenses within the matrix. The depth estimation results are stored under the directory Depth_evaluation_result, which is for reference only.