All Projects → EGjoni → Everything-Will-Be-IK

EGjoni / Everything-Will-Be-IK

Licence: MIT license
A Robust Inverse Kinematics Library

Programming Languages

HTML
75241 projects
java
68154 projects - #9 most used programming language

Projects that are alternatives of or similar to Everything-Will-Be-IK

ossos
Webbased Character Animation System
Stars: ✭ 158 (+351.43%)
Mutual labels:  inverse-kinematics, armature
HybrIK
Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021
Stars: ✭ 395 (+1028.57%)
Mutual labels:  inverse-kinematics, pose-estimation
ailia-models
The collection of pre-trained, state-of-the-art AI models for ailia SDK
Stars: ✭ 1,102 (+3048.57%)
Mutual labels:  pose-estimation
FastPose
pytorch realtime multi person keypoint estimation
Stars: ✭ 36 (+2.86%)
Mutual labels:  pose-estimation
indi-3rdparty
INDI 3rd Party drivers repository
Stars: ✭ 90 (+157.14%)
Mutual labels:  ccd
pytorch-PyraNet
Pytorch version reinplement code of PyraNet , for paper : Learning Feature Pyramids for Human Pose Estimation
Stars: ✭ 32 (-8.57%)
Mutual labels:  pose-estimation
Robotlib.jl
Robotics library written in the Julia programming language
Stars: ✭ 32 (-8.57%)
Mutual labels:  inverse-kinematics
android tflite
GPU Accelerated TensorFlow Lite applications on Android NDK. Higher accuracy face detection, Age and gender estimation, Human pose estimation, Artistic style transfer
Stars: ✭ 105 (+200%)
Mutual labels:  pose-estimation
Keypoint Communities
[ICCV '21] In this repository you find the code to our paper "Keypoint Communities".
Stars: ✭ 255 (+628.57%)
Mutual labels:  pose-estimation
posture recognition
Posture recognition based on common camera
Stars: ✭ 91 (+160%)
Mutual labels:  pose-estimation
GA SLAM
🚀 SLAM for autonomous planetary rovers with global localization
Stars: ✭ 40 (+14.29%)
Mutual labels:  pose-estimation
poseviz
3D Human Pose Visualizer for Python
Stars: ✭ 68 (+94.29%)
Mutual labels:  pose-estimation
latent-pose-reenactment
The authors' implementation of the "Neural Head Reenactment with Latent Pose Descriptors" (CVPR 2020) paper.
Stars: ✭ 132 (+277.14%)
Mutual labels:  pose-estimation
terran
A human perception library
Stars: ✭ 98 (+180%)
Mutual labels:  pose-estimation
GaitGraph
Official repository for "GaitGraph: Graph Convolutional Network for Skeleton-Based Gait Recognition" (ICIP'21)
Stars: ✭ 68 (+94.29%)
Mutual labels:  pose-estimation
Awesome-Vision-Transformer-Collection
Variants of Vision Transformer and its downstream tasks
Stars: ✭ 124 (+254.29%)
Mutual labels:  pose-estimation
Openpose-based-GUI-for-Realtime-Pose-Estimate-and-Action-Recognition
GUI based on the python api of openpose in windows using cuda10 and cudnn7. Support body , hand, face keypoints estimation and data saving. Realtime gesture recognition is realized through two-layer neural network based on the skeleton collected from the gui.
Stars: ✭ 69 (+97.14%)
Mutual labels:  pose-estimation
HPRNet
Bottom-up whole-body pose estimation method in constant time.
Stars: ✭ 51 (+45.71%)
Mutual labels:  pose-estimation
MSPN
Multi-Stage Pose Network
Stars: ✭ 40 (+14.29%)
Mutual labels:  pose-estimation
PCLoc
Pose Correction for Highly Accurate Visual Localization in Large-scale Indoor Spaces (ICCV 2021)
Stars: ✭ 37 (+5.71%)
Mutual labels:  pose-estimation

Everything-WIll-Be-IK

'Everything Will Be IK' is a robust Inverse Kinematics library.

See here for a demo: https://youtu.be/y_o34kOx_FA

It relies on a novel (I'm still writing an explainer) highly stable generalization of CCD.

Features:

  • Position AND orientation targets (6-DOF).
  • Highly stable.
  • Multiple end-effector support
  • Intermediary effector support.
  • Dampening (stiffness control).
  • Target weight/priority (per target, per degree of freedom).
  • Highly versatile 3-DOF constraints with arbitrarily shaped orientation regions.
  • "Soft" constraint support, allowing joints to meet the target in the least uncomfortable way.

The code is quite fast and suitable for realtime use in most graphics applications. A fully constrained humanoid torso effectored at the hips, hands and head (simultaneously trying to reach all four corresponding targets in position and orientation) will solve in well under a millisecond (roughly 0.2 milliseconds on an 8 year old mid-level consumer grade CPU). But further optimizations are likely still possible with data-structure tweaks.

Please let me know if you find bugs you can't fix. Please commit back changes for any bugs you do fix.



DISCLAIMER: This code was intended primarily for graphics applications and has not been thoroughly tested for use in robotics. Until this disclaimer disappears (or you have independently verified it is suitable for your purposes) please do not use this code to command any servos that can put out enough torque to cause damage to people, property, or other components in your build.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].