This repository is an implementation of paper "OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation".
Peng Li, Jiayin Zhao, Jingyao Wu, Chao Deng, Yuqi Han, Haoqian Wang, Tao Yu
Tsinghua University
- Set the hyper-parameters in
option.py
if needed. We have provided our default settings in the realeased codes. - Run
train.py
to perform network training. - Checkpoint will be saved to
./checkpoints/
. - If you want to train the network with the HCI dataset, place the input LFs into
/dataset/hci_dataset
.
- Place the input LFs into
./dataset
(see the attached example). - Run
test.py
to perform inference on each test scene. - The result files (i.e.,
general_52_eslf_depth.tif
) will be saved to./results/OPENet/latest/scan_LF/
.