Abstract

A medium-scale synthetic 4D Light Field video dataset for depth (disparity) estimation. From the open-source movie Sintel. The dataset consists of 24 synthetic 4D LFVs with 1,204x436 pixels, 9x9 views, and 20–50 frames, and has ground-truth disparity values, so that can be used for training deep learning-based methods. Each scene was rendered with a clean pass after modifying the production file of Sintel with reference to the MPI Sintel dataset.

Click here for image samples. (Our project page)

Updates

11th FEBRUARY 2021

The datasets containing 9x9 views are now available! Please check Sintel_LFV_9x9_with_all_disp.zip and Sintel_LFV_9x9.zip.
26th NOVEMBER 2020

Welcome to the Sintel 4D Light Field Video Dataset. The dataset used in our paper is available! Please check Sintel_LFV_cross-hair.zip.

Citation

If you find this useful for your research, please use the following.

==========================================

@inproceedings{kinoshita2021depth,

title={Depth estimation from 4D light field videos},

author={Kinoshita, Takahiro and Ono, Satoshi},

booktitle={International Workshop on Advanced Imaging Technology (IWAIT) 2021},

volume={11766},

pages={117660A},

year={2021},

organization={International Society for Optics and Photonics}

}

==========================================

Dataset Files

Sintel_LFV_9x9_with_all_disp.zip (166.35 GB)
Sintel_LFV_9x9.zip (51.00 GB)
Sintel_LFV_cross-hair.zip (11.85 GB)
Visualized images of disparity value in center view disp_viz_center.zip (15.11 MB)
raw rendering data(.exr/.png) rendering.7z (500.45 GB)

LOGIN TO ACCESS DATASET FILES
Open Access dataset files are accessible to all logged in users. Don't have a login? Create a free IEEE account. IEEE Membership is not required.

QUESTIONS?

Report a problem with this Dataset

Datasets

Open Access

Sintel 4D Light Field Video Dataset