gaussian-splatting icon indicating copy to clipboard operation
gaussian-splatting copied to clipboard

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Results 408 gaussian-splatting issues
Sort by recently updated
recently updated
newest added
trafficstars

When running code, I encountered this issue that seems to occur in the **rasterizer.** Is there any good solution or info for it ? ```Training progress: 2%|█▌ | 600/40000 [00:11

Hey, I am facing a build problem when trying to install SIBR_viewers : ![Screenshot from 2024-04-29 15-18-56](https://github.com/graphdeco-inria/gaussian-splatting/assets/108840691/9d9d6829-55d7-46f9-a5b7-83e2ccc56aa9) any help, i installed all of the packages and followed installation instructions correctly.

Hello, I would like to ask why "hello" is not printed when I print out "hello" in the forward function in "submodules\diff-gaussian-rasterization\diff_gaussian_rasterization\__init__.py", which makes me suspect that I This function...

Hi, I experienced `RuntimeError: an illegal memory access was encountered` when I train 3d gaussian on the T&T dataset. It seems to happen in backpropagation. [Here](https://drive.google.com/file/d/1BN_M84afO6SWgqTa4vbd3QiqGeLzsI9k/view?usp=sharing) is the input of...

I am trying to convert my static render projects to gaussian splats for 6DoF consumption, as they preserve a lot more details compared to other 3D representations such as point...

Hello, Is it possible to improve the rendered depth image by inserting a depth image as input? If there is a way, where can I find it? thank you for...

hello I would also like to learn about a pre-trained model. Can I get flowers or garden data sets other than tandt and db? Did you create point cloud data...

Noticed that in `scene/__init__.py`, the class `Scene` receives a variable `load_iteration`, which seems to support fine-tuning. However, in the following lines: ```{Python} if self.loaded_iter: self.gaussians.load_ply(os.path.join(self.model_path, "point_cloud", "iteration_" + str(self.loaded_iter), "point_cloud.ply"))...

Are there any differences in the rendering results between single and multi-gpu training of 3DGS?