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 139 gaussian-splatting issues
Sort by recently updated
recently updated
newest added

I followed the README and the video at https://www.youtube.com/watch?v=UXtuigy_wYc but i fell in a slump for a few hours due to persistent errors in installing as suggested. As many others...

============================================================================== Global bundle adjustment ============================================================================== iter cost cost_change |gradient| |step| tr_ratio tr_radius ls_iter iter_time total_time 0 1.808163e+05 0.00e+00 9.30e+05 0.00e+00 0.00e+00 1.00e+04 0 2.01e-01 1.23e+00 CHOLMOD version 3.0.14, Oct 22,...

Hi, It seems that there is no consideration of ndc2Pix in the forward process when computing dL_dmean in backward.cu. Is this on purpose or am I misunderstanding something? ![1714121854670](https://github.com/graphdeco-inria/gaussian-splatting/assets/137331394/41238af7-10c8-462d-85d4-259685adc87c)

I didn't have a code environment configured on my computer, and I wondered if anyone would give me a few generated ply files that I used to test the functionality...

Hi, Thanks a lot for sharing your great work. I've built the environment properly and while running the DTU dataset, I try to use the rasterization to render the image....

This is what I get when I try to optimize 308 pictures. I don´t know if they are to much, or should I scale it before or I don't have...

Rendering results are great on truck dataset, but exported point cloud is messy.I can't even find where the truck is. So my question is whether the point cloud derived from...

Hi, I don't understand the result of dSigma_dM = 2 * M. https://github.com/graphdeco-inria/diff-gaussian-rasterization/blob/59f5f77e3ddbac3ed9db93ec2cfe99ed6c5d121d/cuda_rasterizer/backward.cu#L315 I know the M=R@S, and the covariance matrix Sigma=M@transpose(M), but Sigma is a [3,3] matrix, and M...

I am trying to run train.py on my dataset of 1362 pictures of 1600x1300 pixels. When I do I get ``` python /root/gaussian-splatting/train.py -s /Work --iterations 90000 Optimizing Output folder:...