×

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

LLF-Net

Method title

A Lightweight Depth Estimation Network for Wide-Baseline Light Fields

Method description

LLF-Net is a novel end-to-end trainable lightweight network based on the cost volume and attention modules for both wide-baseline and narrow-baseline light field depth estimation, allowing flexible angular inputs.

Camera setup

Cross

Programming language

Python

Runtime environment

Windows, Nvidia GTX 1080 Ti

Additional data

Source code

Additional data

Raw evaluation scores for all scenes

Publication

Title

A Lightweight Depth Estimation Network for Wide-Baseline Light Fields

Authors

Li, Yan and Wang, Qiong and Zhang, Lu and Lafruit, Gauthier

Conference

IEEE Transactions on Image Processing

BibTex

@article{li2021lightweight,
title={A Lightweight Depth Estimation Network for Wide-baseline Light Fields.},
author={Li, Yan and Wang, Qiong and Zhang, Lu and Lafruit, Gauthier},
journal={IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society},
year={2021}
}