Discover @mkocabas Open Source projects

Muhammed Kocabas (@mkocabas)

mkocabas

Stars
5,256
Global Rank 5,089 (Top 0.2 %)
Followers 478
Following 86
Registered almost 11 years ago
Most used languages

Python
81.8 %

Jupyter Notebook
9.1 %

C++
9.1 %

VIBE

Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

EpipolarPose

Self-Supervised Learning of 3D Human Pose using Multi-view Geometry (CVPR2019)

Jupyter Notebook

CoordConv-pytorch

Pytorch implementation of CoordConv introduced in 'An intriguing failing of convolutional neural networks and the CoordConv solution' paper. (https://arxiv.org/pdf/1807.03247.pdf)

PARE

Code for ICCV2021 paper PARE: Part Attention Regressor for 3D Human Body Estimation

pose-residual-network

Code for the Pose Residual Network introduced in 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network (ECCV 2018)' paper

focal-loss-keras

Focal Loss implementation in Keras

body-model-visualizer

GUI for visualization and interactive editing of SMPL-family body models ie. SMPL, SMPL-X, MANO, FLAME.

SPEC

Code for ICCV2021 paper SPEC: Seeing People in the Wild with an Estimated Camera

multi-person-tracker

Simple Multi Person Tracker implementation in PyTorch

yolov3-pytorch

YOLOV3 pytorch implementation as a python package

TrilateralMap

A novel 3D mesh shape descriptor