chaowentao / OccCasNet

OccCasNet: Occlusion-aware Cascade Cost Volume for Light Field Depth Estimation
6 stars 0 forks source link

OccCasNet: Occlusion-aware Cascade Cost Volume for Light Field Depth Estimation

Network Architecture

Network Architecture

SOTA on 4D Light Field Benchmark

Environment

Ubuntu            16.04
Python            3.8.10
Tensorflow-gpu    2.5.0
CUDA              11.2

Train OccCasNet

  1. Download HCI Light field dataset from http://hci-lightfield.iwr.uni-heidelberg.de/.
  2. Unzip the LF dataset and move 'additional/, training/, test/, stratified/ ' into the 'hci_dataset/'.
  3. Stage 1: Run python train_occcas.py
    • Checkpoint files will be saved in 'LF_checkpoints/XXX_ckp/iterXXXX_valmseXXXX_bpXXX.hdf5'.
    • Training process will be saved in
    • 'LF_output/XXX_ckp/train_iterXXXXX.jpg'
    • 'LF_output/XXX_ckp/val_iterXXXXX.jpg'.

Evaluate OccCasNet

Submit OccCasNet

Last modified data: 2023/05/28.

The code is modified and heavily borrowed from LFattNet: https://github.com/LIAGM/LFattNet, SubFocal: https://github.com/chaowentao/SubFocal

The code they provided is greatly appreciated.