Seiun

Thanks for the nice code, it helps a lot! :)

2DGS is actually not optimized specifically for indoor scenes, it doesn't perform well in reconstructing weakly textured areas like white walls, ceilings, etc. Try using something like [GeoGaussian](https://github.com/yanyan-li/GeoGaussian). GeoGaussian uses...

In fact, I found that the point cloud reconstruction of these unbounded scenes was fine, but after visualizing it using SIBR, I could clearly see the errors of alpha, depth...

你可以使用这个[远程查看器](https://github.com/hwanhuh/2D-GS-Viser-Viewer)

> You can see that the distribution of isotropic surfels looks better. and there are less artifacts near the arm of the chair. Although such constraint **may harm the PSNR**,...

> > > You can see that the distribution of isotropic surfels looks better. and there are less artifacts near the arm of the chair. Although such constraint **may harm...

Same question, and I've found that inverse depths are near-large and far-large, whereas monocular depth estimates are usually near-large and far-large. Does the loss function really work?

Use render.py

> > https://drive.google.com/drive/folders/1SJFgt8qhQomHX55Q4xSvYE2C6-8tFll9 从这个链接下载的dtu 数据集中没有 cameras_sphere.npz 这个文件，需要从新生成吗？ > > 请问解决了吗 不影响正常运行吧，我也没有这个文件，得到的结果和PGSR论文里面的也差不多

> > Hey [@kk6398](https://github.com/kk6398) there seems to be some confusion here, all credit to the authors for their excellent work, I am not a co-author of the paper, just an...