Repository files navigation

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

Yu-Ju Tsai,¹ Yu-Lun Liu,^1,2 Ming Ouhyoung,¹ Yung-Yu Chuang^1
1National Taiwan University,²MediaTek

AAAI Conference on Artificial Intelligence (AAAI), Feb 2020

• (Paper Link)
• Contact:r06922009@cmlab.csie.ntu.edu.tw,yulunliu@cmlab.csie.ntu.edu.tw

• We achieveTOP rank performance for most of the error matrices on the benchmark.

• For more detail comparison, please use the link below.
• Benchmark link

Ubuntu            16.04Python            3.5.2Tensorflow-gpu    1.10CUDA              9.0.176Cudnn             7.1.4

• Download HCI Light field dataset fromhttp://hci-lightfield.iwr.uni-heidelberg.de/.
• Unzip the LF dataset and move'additional/, training/, test/, stratified/ ' into the'hci_dataset/'.
• Check the code in'LFattNet_func/func_model_81.py' and use the code at line 247.
• Runpython LFattNet_train.py
  • Checkpoint files will be saved in'LFattNet_checkpoints/LFattNet_ckp/iterXXXX_valmseXXXX_bpXXX.hdf5'.
  • Training process will be saved in
    • 'LFattNet_output/LFattNet/train_iterXXXXX.jpg'
    • 'LFattNet_output/LFattNet/val_iterXXXXX.jpg'.

• Check the code in'LFattNet_func/func_model_81.py' and use the code at line 250.
• Runpython LFattNet_evaluation.py
  • To use your own model, you can modify the import model at line 78 like below:
    • path_weight='./pretrain_model_9x9.hdf5'

@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}}

Last modified data: 2020/09/14.

The code is modified and heavily borrowed from EPINET:https://github.com/chshin10/epinet