Fix data generation error in the referencerun_fmb.py
#33
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
MET-58 Debug convergence issue in JAX-based FMB
I think I made a dumb mistake when porting the reference FMB implementation as they're actually not converging correctly at the moment lol |
|
Looking nice :3 |
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Outdated suggestions cannot be applied.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.
(Closes MET-58)
Background
Turns out I made a mistake when porting over the reference implementation in #6, where in the section that render the g round truth image, I dropped the code that delete the light & camera nodes (because I thought that
r.delete()would delete everything regardless. However, without this cleanup, it seems likepyrenderalways uses the first camera node to render the image, so we end up with a sequence of identical input images, which causes convergence issue.This is fixed by placing back the cleanup code.
Before & After
Before the fix:
Input depth image (generated by
pyrenderer):FMB optimized output:
After the fix:
Input depth image:
FMB optimized output: