Favorites
Pytorch implementation of Multi-View Dynamic Facial Action Unit Detection, Image and Vision Computing (2018)
All Algorithms implemented in Python
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
NiftyMIC is a research-focused toolkit for motion correction and volumetric image reconstruction of 2D ultra-fast MRI.
Code of our MIDL 2018 paper and MedIA extension: https://arxiv.org/abs/1805.04628
The project covers various deep learning models to automate the segmentation of knee cartilages using the diffusion weighted MRI
MIDL 2018 / MEDIA 2019: one binary extremely large and inflecting sparse kernel (pytorch)
This is a 3D Slicer extension for segmentation and spatial reconstruction of infiltrated, collapsed, and emphysematous areas in lung CT.
Efficient 3D human pose estimation in video using 2D keypoint trajectories
Pytorch implementation of R-Transformer. Some parts of the code are adapted from the implementation of TCN and Transformer.
An implementation of attention mechanism using keras
a module for 3D semantic segmentation in point clouds.
visualization code for 3D human body annotation by EFT (Exemplar Fine-tuning)
Recent Transformer-based CV and related works.
Localization -SLAM problem with Extended Kalman filter and Particle filter
Optimized manangement of wood stock of carpentry factories via Particles Swarm and Differential evolution DEGL
Implementation of Active Shape Model in Python (OpenCV).
A pytorch adversarial library for attack and defense methods on images and graphs
Benchmarks of approximate nearest neighbor libraries in Python
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
detectron2 backbone: resnet18, efficientnet, hrnet, mobilenet v2, resnest, bifpn
An elegant Python interface for visualization on the web platform to interactively generate insights into multidimensional images, point sets, and geometry.
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.