Detial of regularizing 2dgs

[Binyr]

Hi,

I use your model to inference normal maps of DTU dataset. And regularize 2dgs normal map after iter 7k with lambda 0.05. The loss is similar to the 2dgs depth_normal regularizing loss. Finnally, I get a slightly different results shown below. Could you provide some details to help me reproduce these results?

Thank you!
Yanrui

[hugoycj]

Hi Yanrui, thanks for providing your reimplmentation result. Over the past three months, we've iteratively updated StableNormal from v0.1 to v0.3, incorporating a more diverse dataset and modifying our pretraining and training techniques. As a result, the 2DGS outcomes may differ significantly from previous versions.

Regarding regularizing loss, you can refer to this PR for details. Our regularization method differs slightly from your implementation, which could also account for some performance variations.

[seulqxq]

Hi, can I ask you how to combine stablenormalX with 2dgs?

[hugoycj]

@seulqxq We have uploaded the train with normal scripts to https://github.com/hugoycj/2d-gaussian-splatting-great-again/blob/main/scripts/train_wmask_wnormal.sh. Feel free to have a try

[seulqxq]

@hugoycj Thank you very much. I will undertake an attempt.

[seulqxq]

@hugoycj Hello, I'm sorry to bother you again, I used 2d-gaussian-splatting-great-again to train my own data set, but there was an error. Could you please tell me if you have ever encountered such a situation?

Here is the structure of my dataset and some versions of the library：
torch 2.3.1+cu118
torchaudio 2.3.1+cu118
mini-dust3r 0.1.2
gaustudio 0.1.0

[hugoycj]

@seulqxq We have a modified mini-dust3r under dev branch https://github.com/GAP-LAB-CUHK-SZ/gaustudio/tree/develop/submodules/mini-dust3r. You can try to install this one

[seulqxq]

Thank you so much for your quick reply! It work