r. tanaka's starred repositories
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
MonocularTotalCapture
Code for CVPR19 paper "Monocular Total Capture: Posing Face, Body and Hands in the Wild"
Kimera-Semantics
Real-Time 3D Semantic Reconstruction from 2D data
awesome-3dbody-papers
😎Awesome list of papers about 3D body
dataset-api
The ApolloScape Open Dataset for Autonomous Driving and its Application.
Kimera-RPGO
Robust Pose Graph Optimization
metashape-scripts
Python scripts for Metashape (former PhotoScan)
video_to_bvh
Convert human motion from video to .bvh
SelecSLS-Pytorch
Reference ImageNet implementation of SelecSLS CNN architecture proposed in the SIGGRAPH 2020 paper "XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera". The repository also includes code for pruning the model based on implicit sparsity emerging from adaptive gradient descent methods, as detailed in the CVPR 2019 paper "On implicit filter level sparsity in Convolutional Neural Networks".
neuralrgbd
Neural RGB→D Sensing: Per-pixel depth and its uncertainty estimation from a monocular RGB video
SingleViewReconstruction
Official Code: 3D Scene Reconstruction from a Single Viewport
holistic_scene_parsing
Code for ECCV 2018 paper - Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image
Translation-Gummy
Translation Gummy is a magical gadget which enables user to be able to speak and understand other languages.
unreal_cv_ros
Unreal CV ROS Perception Simulator
Multiple-Object-Forecasting
Multiple Object Forecasting: Predicting Future Object Locations in Diverse Environments. WACV, 2020
UnrealSteel
Make 3D modeled character imitating user's motion in real time using Unreal Engine, just like REAL STEEL
Agisoft-Metashape-Pro
Python Codes to use with Agisoft PhotoScan Pro processing workflow of aerial photogrammetry.