gaussian-splatting
gaussian-splatting copied to clipboard
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
Installing pip dependencies: / Ran pip subprocess with arguments: ['F:\\ai\\GS\\envs\\gaussian_splatting\\python.exe', '-m', 'pip', 'install', '-U', '-r', 'F:\\ai\\GS\\gaussian-splatting\\condaenv.or9grnh8.requirements.txt', '--exists-action=b'] Pip subprocess output: Processing f:\ai\gs\gaussian-splatting\submodules\diff-gaussian-rasterization Preparing metadata (setup.py): started Preparing metadata (setup.py): finished...
environment: * windows 10 * visual studio 2022 * python 3.9 the information of error report like ``` Processing d:\learn\ai3d\3dgs\dreamgaussian\simple-knn Preparing metadata (setup.py) ... done Building wheels for collected packages:...
Error with gradients when using camera with arbitrary principal points outside of Image Boundaries
Hello, I am currently trying to evaluate the use case of Gaussian Splatting for 3D-Reconstruction based on Satellite Imagery. Unfortunately the process used to approximate the satellite specific camera model...
In the task I'm doing now, the value is extracted with rgb instead of sh, so I need to save the rgb value when I save ply. So the result...
I got this error when training the network. I got colmap data set already, it works well. But when start training, I got this error. Traceback (most recent call last):...
Apologies as this isn't an issue _per se_. I just finished getting training and the local viewer working on Ubuntu 24.04 with CUDA 12. As the process was a little...
I tried to reproduce the FPS number on the mipnerf360 dataset but failed. Specifically, I set up the environments following the instructions in README, and then evaluated the models after...
Executing instruction: "Python render.exe - m output/Output_data" reports an error: File "render.py", line 66, in render_sets(model.extract(args), args.iteration, pipeline.extract(args), args.skip_train, args.skip_test) File "render.py", line 40, in render_sets scene = Scene(dataset, gaussians,...
We are conducting research through 3dgs. (Submodules / diff-guassian-rasterization / cuda_rasterization) I don't know how to do the backpropagation to depth here.
I had a lot of errors during the build but I simply restarted the build and it would progress from the previous checkpoint. However once I got to 95%, specifically...