Self-Supervised Deep Learning for Fisheye Image Rectification

This is the official pytorch implementation of Self-Supervised Deep Learning for Fisheye Image Rectification. The code is written by Byron Hsu and Brian Chao from Department of Electrical Engineering, National Taiwan University. This work is currently in the submission to 2020 ICASSP.

We welcome any advice for this work. Feel free to send issue or PR!

Installation

git clone ...

pip3 install -r requirements.txt

bash train_gcgan.sh [dataset_path] [name]

tensorboard --logdir runs

bash test_gcgan.sh [dataset_path] [name] [which_epoch]

Name	Name	Last commit message	Last commit date
Latest commit ByronHsu update readme Oct 15, 2019 c25bc8f · Oct 15, 2019 History 64 Commits
assets	assets	restructure the code	Oct 15, 2019
data	data	fix testing stage	Oct 9, 2019
experiment	experiment	restructure the code	Oct 15, 2019
models	models	restructure the code	Oct 15, 2019
options	options	restructure the code	Oct 15, 2019
scripts	scripts	Classify adversarially	Oct 12, 2019
util	util	restructure the code	Oct 15, 2019
.gitignore	.gitignore	remove redundant	Oct 15, 2019
README.md	README.md	update readme	Oct 15, 2019
requirements.txt	requirements.txt	restructure the code	Oct 15, 2019
test.py	test.py	restructure the code	Oct 15, 2019
test_gcgan.sh	test_gcgan.sh	add testing score function	Oct 10, 2019
train.py	train.py	update train script	Oct 8, 2019
train_gcgan.sh	train_gcgan.sh	restructure the code	Oct 15, 2019