4DLFVD: A 4D Light Field Video Dataset

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.本研究提出一款由相机阵列采集的4D光场（Light Field, LF）视频数据集，旨在用于设计与测试光场视频编码及处理相关的算法与系统。为采集该类视频，本研究设计并搭建了由100台相机组成的10×10光场采集阵列，单台相机的分辨率为1920×1056。所有视频均在真实且可变的光照条件下采集。该数据集共包含9组光场视频，其中8组采集时相机阵列的位置与朝向均固定不变；最后一组则围绕某一户外特定目标旋转采集获得。每组光场视频均包含100路视频流，且均采用H.265编码格式。数据集涵盖静态场景（如室内盆栽、家具等）与动态场景（如路边车辆、行人等），有效提升了数据集的多样性。作为基准测试方案，本研究给出了自主设计的深度估计方法的测试结果，并验证了该数据集可用于目标检测、三维建模等后续处理与应用场景。