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Outdated suggestions cannot be applied.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.
Dear Gaussian Splatting Lighting Team,
We are the team at deepsense.ai and we are excited to share our recent advancements in CUDA kernel implementations for forward and backward rendering kernels for 3D Gaussian Splattings.
Our forward rendering kernel, an original work by our team, is currently the fastest open-source implementation available. For the backward kernel, we have adapted nerfstudio's gsplat backward implementation to work seamlessly with our forward kernel.
One of our main goals was to maintain the existing API, ensuring that it is trivially easy to replace the vanilla kernels with our optimized versions.
With this pull request, we would like to add support for our custom kernels to your Gaussian Splatting Lighting repository. We believe this integration will enhance the performance and capabilities of the project.
Thank you for considering our contribution.
ds-splat repo: https://github.com/deepsense-ai/ds-splat
Best regards,
The deepsense.ai Team