dzynin Goto Github PK

legcases

The Csvs to create search and graph db for

lexpredict-contraxsuite

LexPredict ContraxSuite

lexpredict-lexnlp

LexNLP by LexPredict

lightweight-human-pose-estimation.pytorch

Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.

lobe

Lobe is the world's first AI paralegal.

lstm_music_generation

Algorithmic music generation using Recurrent Neural Networks (RNNs,) The underlying model is a Many-to-Many Long Short Term Memory (LSTM) with a TimeDistributed Layer.

math3d-react

A user-friendly 3d graphing calculator for the web. Create, share, and animate 3d mathematical scenes.

mediapipe-avatar-js

mediapipe-threejs-jewelery-try-on

mediapipe-to-mixamo

mediapipe landmark to mixamo skeleton

mediapipe_plus

The purpose of this project is to apply mediapipe to more AI chips.

mex_medical_information_extraction

mjolnir-simulator

Like a golf simulator but with mjolnir.

mmhuman3d

OpenMMLab 3D Human Parametric Model Toolbox and Benchmark

mmocr

OpenMMLab Text Detection, Recognition and Understanding Toolbox

mmskeleton

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

mocap-rigging

motion capture data (MediaPipe) rigging with threejs

mocapjs

A motion capture library for Three.js: Playing | Streaming | VR

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

modeler

A Python package to reconstruct 3D models from video

motion-cosegmentation

Reference code for "Motion-supervised Co-Part Segmentation" paper

motion_matrix_evaluation

State of the art for estimation of motion matrix involving pose estimation using mediapipe and dynamic time wrapping.

mprnet

[CVPR 2021] Multi-Stage Progressive Image Restoration. SOTA results for Image deblurring, deraining, and denoising.

mt-dnn

Multi-Task Deep Neural Networks for Natural Language Understanding

mt-dnn-1

Multi-Task Deep Neural Networks for Natural Language Understanding

mujoco

Multi-Joint dynamics with Contact. A general purpose physics simulator.

myblackstone

:black_circle: A spaCy pipeline and model for NLP on unstructured legal text.

networkanalysis

neural-blend-shapes

An end-to-end library for automatic character rigging, skinning, and blend shapes generation, as well as a visualization tool [SIGGRAPH 2021]

neural_renderer

A PyTorch port of the Neural 3D Mesh Renderer