Houdini 21.0 Machine Learning

ML-related nodes for volumes

On this page

ML building blocks

ML Train Volume Upres recipe

Train your own pyro upres model. A trained model can be used to make a lowres pyro sim look more like a highres pyro sim, without actually running a highres pyro sim.

ML Volume Tile Component

Crop tiles from a given volume at one or multiple provided point positions. This is useful for creating training data from 3D volumes. This node is part of the ML Train Volume Upres recipe.

ML Volume Tile Inference

Run an ONNX model on a volume without creating any seams by splitting it up into tiles.

ML Volume Res

Run an ONNX model that was trained using the new ML Train Volume Upres recipe.

ML application

These ML-related nodes incorporate ML in their process either through training data or during inference. They are not intended as building blocks for ML pipelines.

Sparse Billowy Smoke shelf tool

Updated to use ML Volume Upres node to upscale and sharpen the smoke simulation using a pretrained ONNX machine learning model. It creates thick cloud-like smoke rising from a spherical base and is useful as a starting point for simulating scenarios such as chimney smoke or cooling tower steam.

Neural Point Surface SOP

Takes a point cloud as input and reconstructs a VDB surface from it. It contains multiple specialized pretrained models to yield specific looks depending on the material being surfaced. In general, this node should allow users to reconstruct smooth surfaces while preserving the sharp, high frequency, details described by the point cloud.

MPM Surface SOP

Has options to use Neural Model.

Machine Learning

General Support

Supervised ML pipeline tools

ML Recipes

Animation and character-specific ML tools

Volume-specific ML tools

Image-specific ML tools

Reference