In order to load Deep plugin in maya, you will only need to set MAYA_MODULE_PATH variable. However, when deploying Golaem Deep as a Maya module, or on the Render Farm, you may need to set some environment variables.

Notice that some of these variables may already be defined by system or custom scripts. It is then recommended not to replace the existing value, but append the Golaem related value to the existing value, using the appropriate separator (a ";" separator on Windows or a ":" separator on Linux).

Licence Variables

Maya Module Variable

When using advanced deployment, it may be needed to set this variable for Maya to find and load the Golaem module.

Third Party Variables

These variables are mandatory for Golaem to work correctly and their values should be checked in case a problem arise. However, they should never need to be set manually, as they are set by the Golaem Maya Module file.

They are here for your reference when investigating a problem, for people wanting to control them in their own scripts or render with stand-alone versions of their renderer.

Generic Variables

The following variables are mandatory in order to successfully load the Golaem plugin and are required to render with any of the rendering engine listed below:

Deep Deformer Goal

Golaem Deep Deformer aims to replace some rig parts where the non linear deformations are costly. In such case, our deformer using deep learning technics, can learn, then replace, all the deformations, based on the inputs you will select, usually your macro rig inputs (joints, manipulators in local space, weights, etc.).
 

Without Golaem Deep Deformer

With Golaem Deep Deformer

The Deep Deformer can handle several meshes in the same model, to avoid mutiplying the models for simple assets made of numerous meshes.

Deep Deformer can also be used with the Golaem Crowd plugin, to overcome some Crowd blendshapes limitations, and bring all the RIG deformations to screen even for crowd characters.

How it works (without the math)

The deformer uses several deep learning models.

One model is in charge of learning the deformation of each vertex based on its neighbours. We call it the Differential Model. It is a heavy model that is usually trained and evaluated on GPU to save procesing time. However for really small models, or if CUDA is not available, CPU training and evaluation could be an option.

In order to work, this model needs some mesh space vertices positions as reference. Thoses are called Anchors, and by default they are only picked randomly in the vertex indices range. For each Anchor, a very small model, called subspace model, is trained to predict the absolute deformation (in mesh space) of this vertex according to rig inputs. Those models are usually trained and evaluated (infered) on CPU as they are very light.

After some math, everything is put back together at inference time, after evaluating each model.

Framework typical sequence

As each studio may have different usage, user is responsible of the model configuration and training. This is done is several steps :

• Configuration of the target mesh, and creation of its "skinCluster only", linearly deformed, mesh.
• Configuration of required RIG Inputs (joints, manipulator matrices, weights), 
• Extraction of samples, made of n frames of (RIG inputs + vertices of target mesh + vertices of linear mesh)
• Training of the model
• Deployment of the model as a deformer on top of the linear mesh.