QiQi's repositories
ImageRegistration
A demo that implement image registration by matching SIFT descriptors and appling RANSAC and affine transformation.
GNN-Pytorch
GNN方法和模型的Pytorch实现。Pytorch implementation of GNN.
RL-Python-Pytorch
《强化学习-原理与Python实现》的Pytorch实现。
ImageCrawler
Crawl images from baidu, bing, google according to keyword using browser.
BTClassification
Brain tumor classification on structural MR images of BraTS dataset based on 3D Multi-Scale Convolutional Neural Network, which is a part of my master thesis project.
CellDetection
A course project that detect cells in image by a simple full convolution neural network. The project is driven by TensorFlow.
ADDetection
Alzheimer's Disease Detection from structural brain MR images of ADNI dataset by 3D Multi-Scale Convolutional Neural Network, which is a part of my master thesis project.
CTReconstruction
Matlab code for: 1. reconstructing CT image by applying back projection, filtered back projection and convolution back projection; 2. maximum intensity projection.
MLAlgorithms
Python implementations of conventional Machine Learning Algorithms.
ReadWiki-ZH
Convert WIKI dumped XML (Chinese) to human readable documents in markdown and txt.
AdversarialAttack
Attack models that are pretrained on ImageNet. (1) Attack single model or multiple models. (2) Apply white-box attacks or black-box attacks. (3) Apply non-targeted attacks or targeted attacks.
BCIStainer
A stainer translates HE stained slices to IHC stained slices. A solution for Breast Cancer Immunohistochemical Image Generation Challenge.
GoRosalind
Solutions of Bioinformatics Problems in Rosalind Using GoLang primarily.
Hackerrank_Python
Implementations of HackerRand problems, including 30 Days of Code, 10-days-of-statistics, Algorithm and Project Euler +.
Algorithms
Implementations of algorithms in the book "Algorithms Fourth Edition".
Flutter0to1
前端经验基本为0，学习使用Flutter制作Android APP。:full_moon::waning_gibbous_moon::last_quarter_moon::waning_crescent_moon::new_moon::waxing_crescent_moon::first_quarter_moon::waxing_gibbous_moon::full_moon:
github-readme-stats
:zap: Dynamically generated stats for your github readmes
MocapNET
We present MocapNET, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance
PASTA-GAN
Official code for NeurIPS 2021 paper "Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GAN"
pose-with-style
[SIGGRAPH Asia 2021] Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN
VQ-Diffusion
Official implementation of VQ-Diffusion
x-unet
Implementation of a U-net complete with efficient attention as well as the latest research findings