Ghost-DeblurGAN
This is a lightweight GAN developed for real-time deblurring. The model has a super tiny size and a rapid inference time. The motivation is to boost marker detection in robotic applications, however, you may use it for other applications definitely. (by York-SDCNLab)
DeblurGANv2
[ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang (by VITA-Group)
Ghost-DeblurGAN | DeblurGANv2 | |
---|---|---|
1 | 1 | |
35 | 976 | |
- | 2.8% | |
3.4 | 0.0 | |
8 months ago | almost 2 years ago | |
Python | Python | |
MIT License | GNU General Public License v3.0 or later |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
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.
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.
Ghost-DeblurGAN
Posts with mentions or reviews of Ghost-DeblurGAN.
We have used some of these posts to build our list of alternatives
and similar projects.
-
Apriltag pose detection on curved surface
You could try some sort of Image restoration GAN to produce a modified output of the input image (which lies on the curved surface). I have conducted research on GANs for deblurring Fiducial markers, and simply put, the Network takes a blurred image containing fiducial markers and outputs a ‘deblurred image’ whose fiducial markers can be more easily detected. However, keep in mind that the GANs can perform a wide variety of operations on an input Image (other than just deblurring), hence, they are called Image restoration networks in general. What you could give a shot is, create a pipeline where the captured image goes into the GAN, then the output is fed to the Apriltag detector. Here is the link to our GitHub if you need a starter: https://github.com/York-SDCNLab/Ghost-DeblurGAN, and some of my other suggestions are NAFNet and HINet.
DeblurGANv2
Posts with mentions or reviews of DeblurGANv2.
We have used some of these posts to build our list of alternatives
and similar projects.
-
Implementing a CNN on an FPGA
I am trying to implement an image deblurring model (DeblurGANv2) The generator takes blurred images as an input and outputs the corrected image, the discriminator helps in training the generator. The model has been trained and I have run and deblurred images on a GPU. I am completely new to the domain of Machine learning and I am trying to implement this on an FPGA. I wanted your guys help on how to do this. The .h5 files contains the weights of the NN, how do I figure out its structure and put it on my FPGA. Can you please suggest some tools that might help or github links for people who have implemented similar stuff.
What are some alternatives?
When comparing Ghost-DeblurGAN and DeblurGANv2 you can also consider the following projects:
StyleGAN.pytorch - A PyTorch implementation for StyleGAN with full features.
pix2pixHD - Synthesizing and manipulating 2048x1024 images with conditional GANs
DE-GAN - Document Image Enhancement with GANs - TPAMI journal
Pix2Vox - The official implementation of "Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images". (Xie et al., ICCV 2019)
ALAE - [CVPR2020] Adversarial Latent Autoencoders
XVFI - [ICCV 2021, Oral 3%] Official repository of XVFI
tapnet - Tracking Any Point (TAP)
pi-GAN-pytorch - Implementation of π-GAN, for 3d-aware image synthesis, in Pytorch
NAFNet - The state-of-the-art image restoration model without nonlinear activation functions.