It's like Shape Editor in Maya but works with skeletons (transforms).

Last update: Nov 11, 2022

Related tags

Overview

Skeleposer

What is Skeleposer?

Briefly, it's like Shape Editor in Maya, but works with transforms and joints. It can be used to make complex facial rigs based on joints. It's especially good for game engines and realtime graphics.

Basic workflow

Create skeleposer node.
Each node can control large number of bones.
Create joints and add them to skeleposer by pressing "Add joints" button.
You can add/remove joints any time you like.
Just make sure that by removing joints you also remove these joints from pose deltas.
Work with poses.
In practice, you work with skinCluster and poses at the same time.
Connect controls to the poses using drivers.
This is a convenient way of connecting controls to poses.

Features

Skeleposer supports a lot of cool features that make the working process nice:

UI is very similar to Shape Editor.
Duplicate/mirror/flip poses.
You make a facial rig on the left side, then just duplicate & flip to mirror the rig on the right side.
Corrective poses.
You see some poses are combined ugly? No problem, make a corrective pose just like you do it in Shape Editor!
Inbetween poses.
It can be used to activate poses in the middle of another pose activation.
Drivers.
It's unified interface for control connections to poses.
Directories and hierarchies.
You can duplicate/mirror/flip whole folders with poses.
Two blend modes for poses, additive and replace.
Additive is the default mode. Replace mode can be used to replace previous transformations.
For example, such a situation occurs when you want to close wings from any position.
Very fast for complex facial rigs.
The whole facial rig can be evaluated less then 1ms.
Final rig is very simple.
Actually there is a single node called skeleposer does the job. It keeps all the poses each one is very lightweight. So the rig file is really small.

Actually the whole facial rig can be just as simple as a sequence of poses and correctives.
Skeleposer can be transferred into another character as the topology doesn't matter and initial bones positions can easily be adjusted without breaking the system.

Correctives

All corrective poses must be placed below other poses. This is a requirement as corrective poses work like patches.

How to run

Compile C++ plugin

You need Visual Studio and CMake.

Python script

Add skeleposerEditor folder to your scripts path and run the following:

import skeleposerEditor
skeleposerEditor.skeleposerWindow.show()

Additional nodes

There are some other nodes provided by the plugin.

blendMatrix.
This node can be used to blend two matrices. This is done with the following approach:
a) Translation is linear.
b) Rotation is blended with slerp.
c) Scale is linear.
stickyMatrix.
This node is used to make "sticky rig" for two indepdendant transforms. It's useful for eye blink, sticky lips (zip) and other stuff.
Use stickyMatrix module in Rig Builder as a reference: https://github.com/azagoruyko/rigBuilder/blob/main/modules/Tools/StickyMatrix.xml

Your facial rigs

It would be very interesting to see your facial rigs done with Skeleposer! Don't be shy to send me your work to [email protected].

Like Dirt-Samples, but cleaned up

Clean-Samples Like Dirt-Samples, but cleaned up, with clear provenance and license info (generally a permissive creative commons licence but check the

39 Nov 30, 2022

Like ThreeJS but for Python and based on wgpu

pygfx A render engine, inspired by ThreeJS, but for Python and targeting Vulkan/Metal/DX12 (via wgpu). Introduction This is a Python render engine bui

139 Jan 7, 2023

Opinionated code formatter, just like Python's black code formatter but for Beancount

beancount-black Opinionated code formatter, just like Python's black code formatter but for Beancount Try it out online here Features MIT licensed - b

16 Oct 11, 2022

Hand gesture recognition based whiteboard that allows you to write on live webcam. This is the first version and has features like 4 different colors, eraser and a recording option that records your session and saves it in a "recordings" folder. Use index finger to draw and two or more fingers to move around and select items. Future version will contain more functionalities like changeable thickness, color palette, integration with zoom and google meet etc.

hand-write Hand gesture recognition based whiteboard that allows you to write on live webcam. This is the first version and has features like 4 differ

27 Dec 16, 2022

It's like Shape Editor in Maya but works with skeletons (transforms).

Related tags

Overview

Skeleposer

Basic workflow

Features

Correctives

How to run

Compile C++ plugin

Python script

Additional nodes

Your facial rigs

You might also like...

Like Dirt-Samples, but cleaned up

Like ThreeJS but for Python and based on wgpu

Opinionated code formatter, just like Python's black code formatter but for Beancount

a simple, efficient, and intuitive text editor

A simple editor for captions in .SRT file extension

DeFMO: Deblurring and Shape Recovery of Fast Moving Objects (CVPR 2021)

Code for "Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks", CVPR 2021

Implementation of "Deep Implicit Templates for 3D Shape Representation"

Releases(v1.0.0)

v1.0.0(Apr 30, 2022)

Owner

Alexander Zagoruyko

CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection

Rule based classification A hotel s customers dataset

PyTorch version repo for CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes

v objective diffusion inference code for JAX.

This repository compare a selfie with images from identity documents and response if the selfie match.

Repository features UNet inspired architecture used for segmenting lungs on chest X-Ray images

A curated list of awesome Deep Learning tutorials, projects and communities.

《Single Image Reflection Removal Beyond Linearity》(CVPR 2019)

1st place solution in CCF BDCI 2021 ULSEG challenge

THIS IS THE **OLD** PYMC PROJECT. PLEASE USE PYMC3 INSTEAD:

FB-tCNN for SSVEP Recognition

VQMIVC - Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion

3D-Transformer: Molecular Representation with Transformer in 3D Space

Source code to accompany Defunctland's video "FASTPASS: A Complicated Legacy"

Python package to add text to images, textures and different backgrounds

Data augmentation for NLP, accepted at EMNLP 2021 Findings

[ICCV 2021] Deep Hough Voting for Robust Global Registration

This repository contains the entire code for our work "Two-Timescale End-to-End Learning for Channel Acquisition and Hybrid Precoding"

An educational resource to help anyone learn deep reinforcement learning.

Fast, flexible and fun neural networks.

THIS IS THE OLD PYMC PROJECT. PLEASE USE PYMC3 INSTEAD: