BCC+ Frame Fixer ML

BCC Image Restoration

Browse Continuum Effects List

The BCC+ Frame Fixer ML filter uses an AI/ML engine to repair frames that display various types of damage in video source clips, for example, photo flash frames, digital media glitches, degraded archival frames, or capture errors. It can also be used to hide jump cuts and for stylistic temporal effects.

Typical use of the filter might include video shoots at celebrity events, such as film premieres or social gatherings, where stars and dignitaries are subject to flash photography while being recorded on video. Broadcasters who show video with photo flash frames are required by law in some countries to display a warning banner when showing this type of content as it can cause issues for viewers with certain medical conditions.

This filter is a delight to use and the repair operation is fully automated, only requiring the user to select which frames in the shot to fix.

Quickstart Guide for Using the Filter:

  • Apply the Frame Fixer ML filter to a clip that has frames which need to be repaired.
  • Navigate to the first bad frame in the timeline.
  • Click on the Set Bad Frame button to set the Bad Frame slider to the current frame number.
    * If more than one consecutive frame needs to be repaired, use the Repair Duration to set the number of sequential frames that will be replaced.

Important Note: in cases where there is more than a single instance of bad frames that need to be fixed, a hold or shelf style keyframe should be added to the Set Bad Frame parameter at each non-contiguous position in the timeline where frames are being repaired.

Presets and the FX Editor

The FX Editor provides a convenient way to store and retrieve factory installed and/or user generated filter presets. To select a preset, open the FX Editor interface and pick one from the Presets panel. Click the apply button in the FX Editor to return to the host user interface.

To save a custom preset, click the “Create Custom Preset” icon in the top right corner of the parameter list, next to the filter name, set a name for the new custom preset in the dialog that appears and click done.

Mocha Mask and Track, and the Pixelchooser

Mocha Mask and Track provides a way for the user to select and track which pixels in the filtered source are actually going to be affected by the filter, via the generation of image based mattes, gradient mattes and vector shape masks. Mocha planar tracking and vector shape masking options are included in the PixelChooser, which allows for the generation of motion-tracked mask shapes as a hold-back mask.

For more information on the Mocha Masking and Tracking, Click Here.

Compare Mode

The BCC Compare Mode provides a convenient mechanism to compare the effect result with the original source layer. It provides several variations on basic split-screen views with the filtered clip placed next to the unedited original.

For more information on the Compare Mode, Click Here.

Filter Parameters

Model: Used to select the desired frame fix model.

Alpha Aware: Preserves alpha channel information when enabled. Disable when working with non-alpha source shots to improve performance

Set Bad Frame: Used to instruct the filter as to which frame(s) to fix. Should be set to the first bad frame if using Repair Duration to repair more than one contiguous group of frames.

Bad Frame: Used to instruct the filter as to which frame(s) to fix and is automatically filled with the current frame when the Bad Frame button is used. 

Repair Duration: Used to set the number of frames to be fixed 

Mix with Original: Blends the filtered result with the original unfiltered source clip.

GPU Rendering: This popup allows toggles renderer in use for the filter.

  • Default: By default the filter will utilize the installed video card and bases the render on the project settings.
  • 16 Bit Float: Sets the render to 16 bit float
  • 32 Bit Float: Sets the render to 32 bit float
  • Disabled: Disables GPU rendering and switches to software rendering.

Please select your language

The website is currently localized into the following languages