shenxia123

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

PyTorch-GAN

PyTorch implementations of Generative Adversarial Networks.

MIRNet

[ECCV 2020] Learning Enriched Features for Real Image Restoration and Enhancement. SOTA results for image denoising, super-resolution, and image enhancement.

Sparse-Depth-Completion

Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st place on KITTI) [MVA 2019]

DDRNet

The official implementation of "Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes"

deep_image_prior

Image reconstruction done with untrained neural networks.

freemodbus

A Modbus ASCII/RTU and TCP implementation

RCDNet

【CVPR2020, Interpretable Network】A Model-driven Deep Neural Network for Single Image Rain Removal

NAS-DIP-pytorch

[ECCV 2020] NAS-DIP: Learning Deep Image Prior with Neural Architecture Search

ResNet50-Unet

Segmentation for vertebra in MR images

uformer-pytorch

Implementation of Uformer, Attention-based Unet, in Pytorch

TMUnet

Contextual Attention Network: Transformer Meets U-Net

SOMatch

A Framework for Deep Learning-based Sparse SAR-Optical Image Matching

Image-Restoration

Image registration using pytorch

Image-Restoration-deep-learning

Restoring images of damaged paintings using in-painting. Damaged paintings have discolored patches where the paint has faded or fallen off. This project uses image in-painting to fill and restore these lost regions. The models include context-encoders, GANS, conditional GANS and pixel diffusion.

ModBus

Library for Modbus, master/slave, ASCII/RTU, C language, for STM32 and most platform

Transformer-Unet

Unet implementation with transformer encoder

Image-Reconstruction-for-Multimode-Fiber-Imaging-System

Reconstruct original image from distorted speckle pattern with deep learning networks

VAEGAN

try VAE GANLoss + SSIM loss in anomaly Detection

ViTResUNet-Based-Medical-Image-Segmentation

Hybrid CNN-Transformer ViTResUNet is the State of the Art architecture with the backbone of TransUNet. It was presented on the Jamal Nazrul Islam National Conference -2022

Image-Reconstruction-by-Vision-Transformer

This repository is to store developed for task of Image Reconstruction via Vision transfrtomer for tinyImagenet or other small datasets as MNIST

pr-dad

Pytorch implementation of paper: PR-DAD: Phase Retrieval Using Deep Auto-Decoders

Lensless-camera-and-deep-learning-based-image-reconstruction

Dunhuang-Image-Restoration

Dunhuang Image Restoration using partial convolution and SSIM loss

modbus_gd

modbus master and slave support for both tcp/rtu/ascii port from freemodbus

SISR

Single Image Super Resolution Using SRCNN

mse_ccc_corollary

"The Many-to-Many Mapping Between the Concordance Correlation Coefficient, and the Mean Square Error" Preprint here:

Reconstructing-Obfuscated-Facial-Images-Using-CNN

I use Convolutional Autoencoder to reconstruct blurred, pixelated, and speckled facial images

deep-image-prior

Image restoration with neural networks but without learning.

Covid_19_predict

Detecting COVID-19 with Chest X Ray using PyTorch- Resnet-18 with ReLU replaced with Mish and Ranged Adam