Houdini 22.0 Nodes Copernicus nodes

Neural Cellular Automata Decode Copernicus node

Decodes a cell state from the Neural Cellular Automata Core into a visible pattern.

On this page
Since 22.0

This node takes the cell state output from a Neural Cellular Automata Core COP and decodes it into a visible pattern using a decoder neural network. The cell state produced by the core node is a high-dimensional latent representation, so this node is required to convert it into an RGB output.

This node can also upres the decoded result by the specified Upres Factor.

The NCA inference workflow is made up of the Neural Cellular Automata Core COP and the Neural Cellular Automata Decode COP. See Neural Cellular Automata for more information about these nodes, including recipes. See ML Train Neural Cellular Automata for information about how to train an NCA model.

Tip

In some workflows you may want two Neural Cellular Automata Decode COPs. One with an Upres Factor of 1x and the other set to the desired output scale. This quickly iterates on a proxy resolution output that already has the correct colors. This way you only have to pay the cost of running the more expensive high resolution decode after finalizing your simulation setup.

Parameters

Model

Controls where the decoder model comes from.

From Metadata

Uses the decoder model referenced in the layer metadata of the incoming cell state. This automatically matches the decoder to the model used by the upstream Neural Cellular Automata Core.

Note

This is the default setting. In this mode, the node looks for the decodemodel string layer property to know from where it should load the decoder ONNX model file. The node won’t know which model to load if this layer property is removed. You can always set the model file path explicitly.

Custom

Use a custom decoder ONNX file.

Decoder Model File

The path to a custom decoder ONNX model file.

Reload Model

Forces a reload of the ONNX model file.

Upres Factor

The factor by which to upsample the cell states before decoding.

1x

No upressing, just decoding

2x

2 times the input resolution.

4x

4 times the input resolution.

8x

8 times the input resolution.

Filter

The filter used when upsampling the incoming cell states.

See Filters for more information.

Point

Sets the pixel value to the pixel value of the nearest neighbor.

Bilinear

Sets the pixel value through bilinear interpolation .

Box

Sets the pixel value through a box filter, done by sampling all pixels within a box on the original image’s matching pixel.

Bartlett

Sets the pixel value through interpolating according to a triangular window or a Bartlett window , taking each pixel as a sample of this signal.

Catmull-Rom

Sets the pixel value through a bicubic spline known as the Catmull-Rom spline . This is a special case of the Mitchell-Netravali filter .

Mitchell

Sets the pixel value through a bicubic spline known as the Mitchell-Netravali filter.

B-spline

Sets the pixel value through a bicubic spline known as the B-spline . This is a special case of the Mitchell-Netravali filter.

Post Processing

Color Transform

The color transformation to apply to the input image before processing.

OCIO

Use OpenColorIO to transform colors to the target space (Output Space). See Color management in Houdini for more information.

None (Raw)

Don’t apply any color transformation. The default NCA output colorspace is Linear rec709.

Output Space

The output color space to which the NCA colors are transformed.

Advanced

Max Tile Size

The maximum tile size in pixels to use when decoding the cell state. Smaller tiles use less memory, but may be slower due to overhead. Larger tiles are faster, but require more GPU/CPU memory.

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.

Device ID

This parameter can be used to specify which GPU to use for inference when multiple GPUs are available. It has no effect when using CPU inference.

Inputs

cells

The cell state from a Neural Cellular Automata Core node.

Outputs

result

The decoded RGB image.

See also

Copernicus nodes