Optimize selfie segmentation mask for green screen #1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Uses the raw size mask from selfie segmentation. This is generally much smaller than the image, and it can be scaled when drawn. - Stores the mask in an A8 image. This uses less memory and can be drawn with a ColorMatrixColorFilter to restore it to RGBA - Uses line buffer to read from the selfie segmentation mask buffer to keep memory localized while performing conversion from floats to bytes. - Reduces allocations by reusing buffers used for mask conversion These optimizations reduced the selfie segmentation mask logic from ~24ms to < 8ms on a Pixel 9. Further optimizations are possible, but will require more drastic changes to the drawing logic.
donovanfm
approved these changes
May 9, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uses the raw size mask from selfie segmentation. This is generally much smaller than the image, and it can be scaled when drawn.
Stores the mask in an A8 image. This uses less memory and can be drawn with a ColorMatrixColorFilter to restore it to RGBA
Uses line buffer to read from the selfie segmentation mask buffer to keep memory localized while performing conversion from floats to bytes.
Reduces allocations by reusing buffers used for mask conversion
These optimizations reduced the selfie segmentation mask logic from ~24ms to < 8ms on a Pixel 9. Further optimizations are possible, but will require more drastic changes to the drawing logic.