Matte Deflicker ML
Description
A machine-learning deflicker node designed to stabilize temporal behavior in mattes generated by Matte Assist ML/Matte Refine ML. Matte Deflicker ML analyzes consecutive frames for luminance, edge, and density fluctuations, then applies a learned temporal smoothing model that preserves detail while eliminating frame-to-frame jitter. The result is a cleaner, more coherent matte sequence that holds up under fast motion, challenging lighting changes, or thin-edge detail.
Node Group
AI/ML, Key.
Controls
Auto DOD
Auto DOD analyzes the sequence, inserts a DOD (Domain of Definition), and automatically crops the footage based on the incoming alpha to a fixed image size for processing.
Note: Matte Deflicker ML requires a consistent image size throughout the sequence. If your source has a variable resolution, such as a stabilized plate, run Auto DOD first.
Frame Range
Select from All, Work Range or Custom.
Start Frame
With a Custom frame range, selects the start frame.
End Frame
With a Custom frame range, selects the end frame.
DOD Padding %
Controls the percentage of padding around the DOD.
Size Consistency %
Controls how much the DOD box is allowed to change size from frame to frame. At low values the box tightly follows the subject and changes size often. At high values the box stays the same size and provides a more stable working area. The default setting of 50% offers a balance between adaptability and stability.
Static Max DOD
Creates a fixed DOD that covers the combined image or matte bounds over the selected frame range, including DOD Padding. The DOD maintains the same size and position on every frame. Use for variable-resolution sources, such as stabilized plates, so Matte Deflicker ML receives a consistent image size. Size Consistency is disabled when this option is enabled.
Quality
Standard
Performs a single pass refinement.
Enhanced
Performs a three-pass refinement that improves matte quality at the expense of longer render times.
Temporal Range
Sets the number of frames in which to temporally smooth the matte.
Black Clip
Blacks in the matte are made blacker by increasing this value. As the value increases, more values are clipped to black. This is helpful for getting rid of unwanted gray areas in what should be the black part of the matte.
White Clip
Whites in the matte are made whiter by increasing this value. As the value increases, more values are clipped to white. This is helpful for getting rid of unwanted gray areas in what should be the white part of the matte.
Shrink+Grow
Shrinks or grows the matte. Negative values shrink and positive values grow the matte.
Blur
Blurs the matte.
Node Outputs
Output
Outputs the foreground input and generated matte.
Data
When a Matte Assist ML or Matte Refine ML node contains multiple objects, each object is output as its own Cryptomatte layer. Connecting the Data output to another node with a Data input, such as Matte Deflicker ML or Output Multi-Part, keeps those layers intact. The Output Multi-Part node writes each object into its own EXR channel at render, allowing the mattes in the final Cryptomatte EXR file to be individually enabled or disabled in Silhouette’s Cryptomatte node or in other applications that support Cryptomatte, including Nuke and After Effects.