Some questions about dataset format and color model training

[sparshgarg23]

Hi, Thanks for open sourcing the work.I am looking into the method and would like to apply it to a custom dataset. Based on the csv files in PiFUHD and the colab example,I am assuming that this should be the following format of the data

Train
Model_person_1
.obj file
model_person_1.jpg
Model person_1_pose_1
.obj file
model_person_1_pose_1.jpg
Model_person_2
contains an obj file and jog file

TEST
Same format as train

Second question,Let's say I have already created the model using Blender and I would like to use PiFU to just estimate the texture of the clothes,as such can I achieve this by executing train_color_model.py If yes,for evaluation what steps should be followed,because in the current demo script supports both model construction and transfer color.

[ArefMYTB]

Hi, How did you get the model texture in blender exactly like texture in pifu? my models have multiple textures for clothes, eyes, shoes, etc.

[sparshgarg23]

Aref I am actually relying on manual hand crafted UV maps,normals and speculation maps.You can look at the tex file inside dennis_obj to get a better understanding of how to organize the dataset

One such file inside that tex folder looks like this Sorry I am not able to give any more concrete answers as my understanding is still a bit shaky