FUnIE-GAN
Seamoth
FUnIE-GAN | Seamoth | |
---|---|---|
1 | 2 | |
432 | 3 | |
- | - | |
0.0 | 6.7 | |
28 days ago | 5 months ago | |
Python | Python | |
GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
FUnIE-GAN
-
Comparison of detection (with CNN) quality with color restoration of underwater images and without
My diploma's theme has a bit specific application area - sunken technical objects. I have to restorate underwater images. And to prove useability of restoration method for autonomous underwater vechile (AUV) I decided to compare quality of CNN model train with preprocessing and without it. Due to the lack of data I use mirroring by way of augmentation. And to preprocess hundreds of images of images I used this method https://github.com/xahidbuffon/FUnIE-GAN .
Seamoth
What are some alternatives?
iSeeBetter - iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks | Python3 | PyTorch | GANs | CNNs | ResNets | RNNs | Published in Springer Journal of Computational Visual Media, September 2020, Tsinghua University Press
DeepPlastic - Detecting and Quantifying Marine Debris using Deep Visual Models.
prosr - Repository containing an independent implementation of the paper: "A Fully Progressive Approach to Single-Image Super-Resolution"
URSim - Simulator for Unmanned Underwater Vehicles using ROS and Unity3D
sunken-object - Compare quality of binary classification (detection) between natural underwater images and images with restoration
video-quality-metrics - Test specified presets/CRF values for the x264 or x265 encoder. Compares VMAF/SSIM/PSNR numerically & via graphs.
piqa - PyTorch Image Quality Assessement package