Closed fkcptlst closed 7 months ago
I noticed the authors of gaussian-splatting made an overflow bug fix: https://github.com/graphdeco-inria/diff-gaussian-rasterization/commit/f6f13c689327d0ad7fe716f98f5d81f313e11ff6
But this implementation changed it back in this commit. I wonder what are the rationales behind this?
I noticed the authors of gaussian-splatting made an overflow bug fix: graphdeco-inria/diff-gaussian-rasterization@f6f13c6
But this implementation changed it back in this commit. I wonder what are the rationales behind this?
Thanks for pointing it out. This project began shortly after GS was open-sourced. At that time, I implemented the submodule using an earlier version before the GS developers had addressed the proposed bug. Luckily, I didn't experience this bug. Thus, I did not fix it. The reason it appears that I reverted the bug is that I just forked the latest version from November and pasted the submodule we had been using, and pushed it. We plan to fix it with a more robust version when we find the time. However, we welcome contributions and would greatly appreciate it if you would consider submitting a pull request to fix this bug or help enhance this project.
Thanks for the clarification. I'll try patching the fix and see if it works.
I ran into the following exception when I made some modifications on learning rates.
Specifically, the optimization params that I use are as follows:
I've also checked this issue from the original gaussian-splatting repo with little help: https://github.com/graphdeco-inria/gaussian-splatting/issues/24
I wonder if similar issues were encountered before, and what are the possible methods to mitigate this issue?