fvdb update #2040
Merged
fvdb update #2040
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
* Added a fvdb devcontainer so that VSCode and Github Codespaces can run inside the docker environment automatically Signed-off-by: Christopher Horvath <blackencino+git@gmail.com> * Improved the language in the comments Signed-off-by: Christopher Horvath <blackencino+git@gmail.com> * Made suggested configuration changes from VSCode copilot Signed-off-by: Christopher Horvath <blackencino+git@gmail.com> --------- Signed-off-by: Christopher Horvath <blackencino+git@gmail.com>
* Debugging Signed-off-by: Jonathan Swartz <jonathan@jswartz.info> * Clarifying comments Signed-off-by: Jonathan Swartz <jonathan@jswartz.info> * Fix logic in computeGradientState Fixed appropriate sizing of the tensors it writes to Signed-off-by: Jonathan Swartz <jonathan@jswartz.info> * Change the computeGradientState loops over C*N to save on some multiplications Signed-off-by: Jonathan Swartz <jonathan@jswartz.info> * backward test checkpoint Signed-off-by: Jonathan Swartz <jonathan@jswartz.info> * Revert BackwardTest rework Signed-off-by: Jonathan Swartz <jonathan@jswartz.info> * update test data tag Signed-off-by: Jonathan Swartz <jonathan@jswartz.info> * cleanup Signed-off-by: Jonathan Swartz <jonathan@jswartz.info> --------- Signed-off-by: Jonathan Swartz <jonathan@jswartz.info>
…ySoftwareFoundation#344) This remove the last vestiges of glm usage from our code by refactoring any Gaussian Projection Backwards code to use nanovdb::math classes and to cleanup any style/naming conventions on code that is refactored. To that end, several themes of work in this PR include: Removing GLM from our build infrastucture Transitioning the code in GaussianProjectedBackward.cu & GaussianProjectedJaggedBackward.cu to using nanovdb::math in place of glm Adding functionality to nanovdb::math to support a few needed missing operators Removing GaussianTypes.cuh which was used to define glm types for Projection Consolidated any remaining, needed warp-prefix functions from GaussianTypes.cuh and GaussianVectorTypes.cuh into GaussianWarpUtils.cuh Refactored functions in GaussianUtils.cuh to return their calculated results instead of directly modifying output parameters where possible. The return values of these functions is then used by the calling code for modifying variables in the calling code. For instance, instead of add_blur_vjp adding blur to a parameter passed by reference, generateBlurVectorJacobianProduct now builds a nanovdb::Math::Mat2 which is used by the calling code. Add docstrings to GaussianUtils.cuh Moving snake_case variables/functions to camelCase and being more descriptive in their naming Making variable types and names consistent between related functions (forward/backwards) Fixing worldToCamMatrices being mistakenly called camToWorldMatrices --------- Signed-off-by: Jonathan Swartz <jonathan@jswartz.info>
…cameras in computeGradientState (AcademySoftwareFoundation#385) Signed-off-by: Jonathan Swartz <jonathan@jswartz.info>
…mySoftwareFoundation#375) * Replace binary search for computing jidx with nested kernels * Cleanup for CPU implementation
* rewrite colmap dataset Signed-off-by: Francis Williams <francis@fwilliams.info> * named args Signed-off-by: Francis Williams <francis@fwilliams.info> --------- Signed-off-by: Francis Williams <francis@fwilliams.info>
swahtz
merged commit 39d2c17
into
AcademySoftwareFoundation:feature/fvdb
12 of 14 checks passed
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.
No description provided.