In preprocess_image, using consistent cutoff value for bounding box and pre-multiplied alpha #186
Conversation
This file contains 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
…nd pre-multiplied alpha
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Outdated suggestions cannot be applied.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.
The alpha from rembg is not binary. A small foreground object make causing a transition region around the object due to resizing. Binarize the alpha channel with a cutoff value fixes the problem. Also, this cutoff is used in bounding box selection.
Here is an example. Before this change, a wide transition of alpha from 0 to 1 causing the system can't distinguish the foreground and background. The result is a quad shape.
After this change, it's much better in 3D shape.
