Machine Learning

FLAME is a lightweight and expressive generic head model learned from over 33,000 of accurately aligned 3D scans.

Background Matting: The World is Your Green Screen.

TResNet: High Performance GPU-Dedicated Architecture

PyRoss is a numerical library for mathematical modelling of infectious disease in Python. Currently the library supports structured compartment models formulated as systems of differential equations.

Knowledge graphs (KGs) are data structures that store information about different entities (nodes) and their relations (edges).

A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.

This is the code for the CVPR 2020 paper. This code allows for synthesising of new views of a scene given a single image of an unseen scene at test time.

The COVID-19 pandemic continues to have a devastating effect on the health and well-being of the global population. A critical step in the fight against COVID-19 is effective screening of infected patients, with one of the key screening approaches being radiological imaging using chest radiography.

Object detection is a computer technology related to computer vision and image processing that deals with detecting instances of semantic objects of a certain class (such as humans, buildings, or cars) in digital images and videos.

BachGAN: High-Resolution Image Synthesis from Salient Object Layout Yandong Li, Yu Cheng, Zhe Gan, Licheng Yu, Liqiang Wang, and Jingjing Liu In CVPR 2020.

torchlayers is a library based on PyTorch providing automatic shape and dimensionality inference of torch.nn layers + additional building blocks featured in current SOTA architectures (e.g. Efficient-Net).

An elegant, flexible, and superfast PyTorch deep Reinforcement Learning platform.

Models of SEIRS epidemic dynamics with extensions, including network-structured populations, testing, contact tracing, and social distancing.

Image text MNSSp3: A privacy protection sharing platform for medical big data.

Official implementation of the paper Improved Techniques for Training Single-Image GANs" by Tobias Hinz, Matthew Fisher, Oliver Wang, and Stefan Wermter.

The Mayan Adventure is an open-source reinforcement learning environment for Unity ML-Agents.

This repository implements YOLACT: Real-time Instance Segmentation on the FCOS: Fully Convolutional One-Stage Object Detection detector.

Momentum Contrast for Unsupervised Visual Representation Learning.

Implementation of Transformer OCR as described at Scene Text Recognition via Transformer.

WhyNot is a Python package that provides an experimental sandbox for decisions in dynamics, connecting tools from causal inference and reinforcement learning with challenging dynamic environments.

this repo is the reconstruct of original CenterNet. Unlike most implementation base on detectron2 or mmdetection, highly modulized code base makes users hard to understand what's the basic idea going on.

PCDet is a general PyTorch-based codebase for 3D object detection from point cloud.

Randomized Smoothing of All Shapes and Sizes.

In contrast to the literature where local patterns in 3D point clouds are captured by customized convolutional operators.

Search similar images.The similarity between images are modeled by CNN (Convolutional Neural Networks) model.Real-time search by K-D Tree.