×

Algorithm Details

Check out the new Google group to connect with other light field researchers, discuss ideas, and initiate collaborations. Some questions about the benchmark are answered over there as well! There is also a new collection of light field resources. Please feel encouraged to add further links.

go back to table

Acronym

LFattNet

Method title

Attention-based View Selection Networks for Light-field Disparity Estimation

Method description

Using the full grid of light field images
Attention module to select meaningful views
Input : 81 viewpoints(star shape) RGB images

Camera setup

Full grid

Programming language

python

Runtime environment

Ubuntu 16.04, i7-7700 @3.6GHz, 64GB RAM, 1080ti

Additional data

Project website

Additional data

Raw evaluation scores for all scenes

Publication

Title

Attention-based View Selection Networks for Light-field Disparity Estimation

Authors

Yu-Ju Tsai, Yu-Lun Liu, Ming Ouhyoung, Yung-Yu Chuang

Conference

AAAI 2020

BibTex

@inproceedings{Tsai:2020:ABV,
author = {Tsai, Yu-Ju and Liu, Yu-Lun and Ouhyoung, Ming and Chuang, Yung-Yu},
title = {Attention-based View Selection Networks for Light-field Disparity Estimation},
booktitle = {Proceedings of the 34th Conference on Artificial Intelligence (AAAI)},
year = {2020}
}