Visual Attention for Light Fields
13th January 2020
Light fields have become a major research topic in recent years. Even though there are now efforts in different applications such as compression, display, and post-processing, the human visual perception for light fields is rarely studied. In this project, we study the visual attention and saliency aspects for the light fields. There are several challenges to this task. In a recent submission, we try to address these challenges and build a dataset.
This page contains information related to the subjective user study which collected the ground truth visual attention data from the user study participants. Please refer to Light Field Saliency Estimation webpage for our automatic saliency estimation work for light fields.
Downloads
The Light Field Visual Attention Dataset can be downloaded here [Please contact the authors].
Please kindly cite our paper in your publication if you use this database:
- A. Gill, E. Zerman, C. Ozcinar, A. Smolic. “A Study on Visual Perception of Light Field Content” The Irish Machine Vision and Image Processing Conference (IMVIP), 2020.
@inproceedings{gill2020study,
title = {A study on visual perception of light field content},
author = {Gill, Ailbhe and Zerman, Emin and Ozcinar, Cagri and Smolic, Aljosa},
year = {2020},
booktitle = {The Irish Machine Vision and Image Processing Conference ({IMVIP})}
}
Related Publications:
Sorry, no publications matched your criteria.
Additional Results
Due to the page limit of the venue to which we submitted our work, we could not provide all the results in the manuscript. Here we will share additional results for our study.
The data we used were from 4 different databases: Stanford1, EPFL2, Disney3, HCI Heidelberg4.
Scanpaths
| Reference | All-in-focus | Region-1 | Region-2 | Front-to-back | Back-to-front | |
| Boardgames4 |  |
 |
 |
 |
 |
 |
| Church3 |  |
 |
 |
 |
 |
 |
| Couch3 |  |
 |
 |
 |
 |
 |
| Dino4 |  |
 |
 |
 |
 |
 |
| Dishes4 |  |
 |
 |
 |
 |
 |
| Friends2 |  |
 |
 |
 |
 |
 |
| LegoKnights1 |  |
 |
 |
 |
 |
 |
| Mansion3 |  |
 |
 |
 |
 |
 |
| Medieval4 |  |
 |
 |
 |
 |
 |
| Pens4 |  |
 |
 |
 |
 |
 |
| Platonic4 |  |
 |
 |
 |
 |
 |
| Sideboard4 |  |
 |
 |
 |
 |
 |
| Table4 |  |
 |
 |
 |
 |
 |
| Tarot-Large1 |  |
 |
 |
 |
 |
 |
| Tarot-Small1 |  |
 |
 |
 |
 |
 |
| Tower4 |  |
 |
 |
 |
 |
 |
| Town4 |  |
 |
 |
 |
 |
 |
| Treasure1 |  |
 |
 |
 |
 |
 |
| Vespa2 |  |
 |
 |
 |
 |
 |
| Vinyl4 |  |
 |
 |
 |
 |
 |
Video examples for scanpaths
Real-time visualisation for “Front-to-back” focal sweep rendering (LegoKnight1).
Real-time visualisation for “Back-to-front” focal sweep rendering (LegoKnight1).
Heatmaps
| Reference | All-in-focus | Region-1 | Region-2 | Front-to-back | Back-to-front | |
| Boardgames4 | |
 |
 |
 |
 |
 |
| Church3 | |
 |
 |
 |
 |
 |
| Couch3 | |
 |
 |
 |
 |
 |
| Dino4 | |
 |
 |
 |
 |
 |
| Dishes4 | |
 |
 |
 |
 |
 |
| Friends2 | |
 |
 |
 |
 |
 |
| LegoKnights1 | |
 |
 |
 |
 |
 |
| Mansion3 | |
 |
 |
 |
 |
 |
| Medieval4 | |
 |
 |
 |
 |
 |
| Pens4 | |
 |
 |
 |
 |
 |
| Platonic4 | |
 |
 |
 |
 |
 |
| Sideboard4 | |
 |
 |
 |
 |
 |
| Table4 | |
 |
 |
 |
 |
 |
| Tarot-Large1 | |
 |
 |
 |
 |
 |
| Tarot-Small1 | |
 |
 |
 |
 |
 |
| Tower4 | |
 |
 |
 |
 |
 |
| Town4 | |
 |
 |
 |
 |
 |
| Treasure1 | |
 |
 |
 |
 |
 |
| Vespa2 | |
 |
 |
 |
 |
 |
| Vinyl4 | |
 |
 |
 |
 |
 |
Acknowledgement
This publication has emanated from research conducted with the financial support of Science Foundation Ireland (SFI) under the Grant Number 15/RP/2776.
Contact
If you have any question, send an e-mail to gilla3@tcd.ie or zermane@scss.tcd.ie or ozcinarc@scss.tcd.ie.