Algorithm Details

OACC-Net

Occlusion-Aware Cost Constructor for Light Field Depth Estimation

We propose a simple and fast cost constructor to construct matching cost for LF depth estimation. Our cost constructor is occlusion-aware and can handle occlusions by dynamically modulating pixels from different views. Based on the proposed cost constructor, we develop a deep network called OACC-Net for LF depth estimation.

Full 9×9 grid

PyTorch

Raw evaluation scores for all scenes

Occlusion-Aware Cost Constructor for Light Field Depth Estimation

Yingqian Wang, Longguang Wang, Zhengyu Liang, Jungang Yang, Wei An, Yulan Guo

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

@inproceedings{OACC-Net,
title = {Occlusion-Aware Cost Constructor for Light Field Depth Estimation},
author = {Wang, Yingqian and Wang, Longguang and Liang, Zhengyu and Yang, Jungang and An, Wei and Guo, Yulan},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2022}
}