Closed dihuangcode closed 4 years ago
Another question,
You said The module can be used also for inter-penetrations of different meshes - for this the easiest and naive approach (without additional bookkeeping) is to fuse all meshes in a single mesh and treat inter-penetrations as self-penetrations.
I did some experiments according your suggestion, and found the same problem.
In this case, I didn't change optimizer and learning rate. The loss started around 0.00005, then reduced to 0.00003, after 10000 steps.
initial meshes:
meshes after 10000 steps optimization:
plot them in one image, red meshes are new meshes:
My questions:
Thanks a lot ! : )
@Yedis In general, some collisions (e.g. armpit-upper arm) cannot be removed, since SMPL does not model contact-based deformation. In your first example the poses look completely unnatural, so the inter-penetrations make sense. In the second example, which variables are you using for the optimization? Pose and shape(betas)? Did you also include body translation? This would be the easiest thing to change to resolve the collisions between the two individuals.
How to solve inter-penetrations of different meshes, could you please give a detail description? Thanks in advance~
Hi , @vchoutas
Thanks for your awesome work! I just met some questions about your demo script
batch_smpl_untangle.py
.I changed your optimizer from SGD to Adam, and set lr to 0.001, which is a normal configuration. The reason I did this is to optimize faster, since I noticed your original SGD version change little poses even after a lot of optimization.
In most cases, the loss started around 0.00003, then reduced to 0.00001
My questions are as follows :
I guess they are the result of imperfection loss from
Capturing Hands in Action using Discriminative Salient Points and Physics Simulation
, but I am not quite sure.Following is 10000 steps result.