Implement normal consistency loss. #273
Open
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
|
Hi, are there plans to merge this into the main branch? |
|
any updates? |
|
Great work! When it will be available? |
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Outdated suggestions cannot be applied.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.
Implement normal consistency loss for 3DGS. It should be a strong baseline for surface reconstruction. Hyperparameters are from 2DGS and their rasterization backend is wrapped for comparison.
Added numerical tests and support packed mode and sparse grad. Currently, this implementation only supports fused branch of the fully_fused_projection. Not sure what to do about the unfused branch because we can't compute the normals from covar.
TODO:
Visualizations
3dgs w/ consistency (mcmc w/ 3M GSs) (PSNR: 27.25)
3dgs_normal_compress.mov
2dgs w/ consistency (mcmc w/ 3M GSs) (PSNR: 26.84)
2dgs_normal_compress.mov
3dgs w/o consistency (mcmc w/ 3M GSs) (PSNR: 27.62)
