gaussian-splatting
gaussian-splatting copied to clipboard
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
Thanks for the great work on 3D Gaussian Splatting! The rendering results look amazing. I’m trying to export the 3D model in a format that can be opened in Blender...
when I run: python convert.py -s data It report error like this: qt.qpa.xcb: could not connect to display qt.qpa.plugin: Could not load the Qt platform plugin "xcb" in "" even...
`cmake -Bbuild . -DCMAKE_BUILD_TYPE=Release` I overcome some errors before this and it works well for now. but i can't handle this problem. is anyone can help me? after i command...
Recently, I met a strange error. The gaussian splatting fails during runing as follows: > Optimizing > Output folder: ./output/e0d441e3-b [20/11 10:29:01] > Tensorboard not available: not logging progress [20/11...
I am trying to install the gaussian-splatting in colab as given in the repo. While install the file - simple_knn through this line: !pip install -q /content/gaussian-splatting/submodules/simple-knn I am getting...
I would like to ask about the computation of the partial derivative of the loss function `L` with respect to `mean2D` in [`backward.cu`](https://github.com/graphdeco-inria/diff-gaussian-rasterization/blob/main/cuda_rasterizer/backward.cu#L545). There is an additional factor of `0.5W`(`ddelx_dx`)in...
I have two sets of images. One set can be sparsely reconstructed using COLMAP, while the other set fails due to insufficient feature points caused by camera characteristics. I plan...
Hello, I'd encountered an issue when running the convert.py script with Colmap. It seems that the sparse/0 directory is not the final result for the Colmap mapper, and solved it...
Hey guys, I am quite impressed by the visualization capability of Gaussian splatting but quite new to this field. I currently have some Lidar-scanned point cloud with RGB information and...
Dear 3DGS crew, I have encountered difficulty while trying to render a scene up to a specified depth. Instead of simply excluding Gaussians outside of the viewing frustum I defined...