Thanks for your great job!
I want to know why added the accum_rea = last_alpha + (1.f - last_alpha) * accum_rea; dL_dalpha += (1 - accum_rea) * dL_dpixel_alpha; in renderCUDA backward.cu You know that in the gaussian-splatting's code ,this isn't be added. and how can I get the formula about this part.
Hi,
We wanna support the gradient back-propagation of alpha map supervision. Sometimes we have the ground truth alpha map of the scene, and we may compute the l1 loss between the predicted alpha map and GT.
Thanks for your great job! I want to know why added the
accum_rea = last_alpha + (1.f - last_alpha) * accum_rea; dL_dalpha += (1 - accum_rea) * dL_dpixel_alpha;
in renderCUDAbackward.cu
You know that in the gaussian-splatting's code ,this isn't be added. and how can I get the formula about this part.