Nikhil Varma Keetha

Hello, Thank you for reaching out with your query. The TUM data loader returns poses, which are relatively inverse transformed where the first pose would be identity (I) and the...

Hi, Can you potentially try other versions of Python (3.6, 3.7, or 3.9) and CUDA 11.1 or 10.2?

Hi, Thanks for your interest! We provide a version of the dataset here: https://github.com/AnyLoc/AnyLoc#included-datasets

Hi, we use both rendered color and depth loss where the losses are weighted using the silhouette when doing tracking. For details regarding the loss, please refer to the paper...

Hi, we haven't tested on Windows yet. I presume the setup would be similar to the instructions here: https://github.com/graphdeco-inria/gaussian-splatting#local-setup Also, this video might be of help: https://youtu.be/UXtuigy_wYc?si=y87CrnBaZBPyBshL I think the...

Hi, for help with the `diff-gaussian-rasterization` compilation on Windows, I would recommend referring to the 3DGS repo: https://github.com/graphdeco-inria/gaussian-splatting?tab=readme-ov-file#faq Also, I think their closed issues have additional helpful info for Windows.

Potentially helpful for building environment on Windows: https://github.com/spla-tam/SplaTAM/issues/27#issuecomment-1857875316

Thanks for trying out our code! The error relates to not being able to find the config file for the data. You will also need a corresponding config file for...

Hi @small-zeng, Thanks for your interest in our work! We would like to mention that the reported speed for the current version of SplaTAM in the paper (Table 6) is...

Thanks! Yes, updating the code to show live training should be possible. However, we currently don't have this implemented. Furthermore, SplaTAM needs further optimization to enable faster reconstruction. Regarding other...