You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Fortunately, such a full-one matrix with a scaled main diagonal is usually positively defined and symmetric. Thus, the reparameterized $R^TSSR$ is still a covariance matrix.
I have roughly checked that this issue is not so influential to the PSNR performance. If required and agreed, I'm more than glad to submit a hotfix PR for it.
The text was updated successfully, but these errors were encountered:
If there is a single scalar parameter to a vector constructor, it is used to initialize all components of the constructed vector to that scalar’s value. If there is a single scalar parameter to a matrix constructor, it is used to initialize all the components on the matrix’s diagonal, with the remaining components initialized to 0.0.
For this reason, glm::mat3 S = glm::mat3(1.0f); provides identity matrix, not the matrix full of ones.
Hi guys,
I wonder that ths S matrix defined in
computeCov3D
funcs for both fwd/bwd computations is now incorrectly initialized to full-one:diff-gaussian-rasterization/cuda_rasterizer/forward.cu
Line 121 in 59f5f77
If I understand correctly, here we expect an identity matrix instead:
Fortunately, such a full-one matrix with a scaled main diagonal is usually positively defined and symmetric. Thus, the reparameterized$R^TSSR$ is still a covariance matrix.
I have roughly checked that this issue is not so influential to the PSNR performance. If required and agreed, I'm more than glad to submit a hotfix PR for it.
The text was updated successfully, but these errors were encountered: