Houdini 21.0 Nodes Geometry nodes

ML Volume Upres geometry node

Increases the resolution of an input volume using an ONNX model

On this page
Since 21.0

Overview

Volume Upres allows you to upscale and sharpen a given input volume using a pretrained ONNX machine learning model. To train new models you can use the ML Train Volume Upres Recipe.

The node takes a VDB or native Houdini volume as an input.

Parameters

Model File

The model file that was trained using ML Train Volume Upres Recipe.

Reload Model

Force a reload of the .onnx file.

Batch Mode

Choose between Multiple Packed and Single (Compiled CPU) mode. Generally Multiple Packed + GPU is the preferred mode, but Single (Compiled CPU) allows for acceptable inference speed on the CPU, when no GPU is available.

Execution Provider

Determines which ONNX execution provider to use for inference. By default, the node attempts to pick the best available provider and prefers to use GPU acceleration.

Automatic

Chooses the best provider for the current system. This option prioritizes CUDA if installed, DirectML/CoreML as a fallback depending on the platform, and CPU inference if no GPU provider is available.

CPU

Perform inference using on the CPU.

CUDA

Perform inference using CUDA/cuDNN. CUDA and cuDNN must be installed using the packages provided by NVIDIA.

DirectML

Only available on Windows. Performs inference using the Windows Direct Machine Learning library.

CoreML

Only available on macOS. Performs inference using Apple’s Core ML library.

Volume

The volume primitives to run inference on.

Pre & Post Processing

Pre Sharpen

Activates pre-sharpening. This is useful to emulate the training data inputs.

Amount

Blends the amount of the sharpening being applied.

Number of Passes

The number of passes to use when sharpening.

Post Sharpen

Activates post-sharpening.

Amount

Blends the amount of the sharpening being applied.

Number of Passes

The number of passes to use when sharpening.

Prune Voxels

Activates voxel pruning.

Prune Tolerance

Defines the pruning threshold.

Mask Voxels

Activates voxel masking.

Tolerance

Defines the masking threshold.

Clamp

Clamps the output voxel values.

Clamp Min

Lower bound of the value range.

Clamp Max

Upper bound of the value range.

Naive Upsample Other Fields

Enables upsampling for the remaining fields using a naive filter approach.

Volumes

The volumes to be upsampled. Leaving this empty upsamples all volumes.

Filter

The type of filter to use when upsampling.

Filter Scale

The filter scale to use when upsampling.

Inputs

Input Volume

A volume to upres using a pretrained ML model and any extra fields.

Outputs

Output Volume

A volume that was upresed using a pretrained ML model and any extra fields.

See also

Geometry nodes