《Lerning n Intrinsic Grment Spce for Interctive Authoring of Grment Animtion》

Hi there, I'm interested in giving this technique a try, but it looks like the data_set folder is empty. Are there more updates we can expect in order to run these examples?

Thanks! -- Paul

Hi there, it's me again. First, I wanted to thank you for providing this working implementation, I was able to run all the example scripts and produce very high quality results! Once I got the networks trained, I've been experimenting a bit to see how well they work on new inputs. Unfortunately, running 06.mie_eval.py on new data, even just a copy of data_set/anim/anim_01/Dude.anim.npy with slight perturbations, created very unstable results. I was digging in to debug the problem, when it occurred to me that 05.mie_train.py is only training on the 800 frames of animation in Dude.anim.py. This doesn't seem like enough data to allow much if any generalization to new motions. Checking the original paper, 30,000 frames of animation was used, which I imagine leads to much better results. Is there any chance you can provide that data set?

Thanks! -- Paul

Hello, I am trying to use your code for my project, but I find something not working as expected in 05.mie_train.py. The function is get_same_material_list().

def get_same_material_list(flist_train, batchsize):

	blst = np.random.permutation(len(flist_train))
	xlst = []
	t = 0

	for i in range(len(blst)):
		if flist_train[blst[i]][1] == flist_train[blst[0]][1]:
			xlst.append(blst[i])
			t=t+1
			if t == batchsize: break

	return xlst

If I understand correctly, the file list is a list of string of file information with the form "case_01 XX 123" "case_01 YY 234", where XX and YY correspond to the simulation parameter and the number indicates the frame number. In line if flist_train[blst[i]][1] == flist_train[blst[0]][1], we try to find mesh files with the same simulation parameter. However, the indexed flist_train[blst[i]] is a string, the second element (use [1] to index) is essentially a character 'a', not XX or YY. The function is trying to get four random data in the training set.

Thanks for your attention.

When generating cloth with new human motions, what is the input? I found the npy_path at line 98 in 06.mie_eval.py is the eval mesh corresponding to the new motion, which means the ground truth. Is it a bug? So what is the input when testing new motions? Maybe a random selected model which has the same material to the ground truth (eval mesh) from the training dataset, but different input may get various result.