DrapeNet
DrapeNet copied to clipboard
Code for "DrapeNet: Garment Generation and Self-Supervised Draping", CVPR2023
The range of dgcnn output is very large, useing tanh() to limit the range smaller, is this better? e.g tanh(old_output) * C (to C, for example1.0~10.0)
I wanted to train the draping network also. Where can i get the code from ???
Hello, can you please tell me where the files body_info_f.npz and body_info_npz in extra-data come from? How are they produced and how to change their content? I would like to...
I'm trying to infer samples from the training samples. While some have perfect retargeting, it seems to be exploding for some samples. The results are attached below. I'm using the...
Thank you for your good work,I want to know how I can reconstruct the garment from the input image
Please share the information related to randomly selected samples from the AMASS dataset for training & evaluation as mentioned in the paper. Also, do you guys plan to release the...
When I run train_encdec.py, I should input base_cfg_dir. What should I fill in? There is no "bases" folder under the "cfg" folder. Thanks
Hello, I have some questions regarding the code in the "Encoder-Decoder" section. Is it used for training and extracting results? Could you provide a pre-trained model for fitting meshes or...
Hello, I was running train_encdec.py. I'm wondering that what content and format train-ids.pkl should contain. Can you show me a example? Moreover, do I need to arrange every CLOTH3D garment...