POSA
POSA copied to clipboard
Populating 3D Scenes by Learning Human-Scene Interaction https://posa.is.tue.mpg.de/
Hi, thank you for the amazing work! I followed the instructions and placed the free rp models (obj) in the `rp_clothed_meshes` folder. Under the same folder there is a tex...
``` Traceback (most recent call last): File "src/affordance.py", line 105, in vertices_org, vertices_can, faces_arr, body_model, R_can, pelvis, torch_param, vertices_clothed = data_utils.pkl_to_canonical( File "/POSA/src/data_utils.py", line 83, in pkl_to_canonical body_model.reset_params(**torch_param) File "/lib/python3.8/site-packages/torch/autograd/grad_mode.py",...
Hi, thank you for the great work! I wonder how you produced files (e.g. A_0.npz) in mesh_ds folder? I would like to produce such files for SMPL and SMIL models,...
Thanks for your amazing work! I notice that in the paper a UE scene is tested using the proposed method, I wonder how to get the corresponding point cloud and...
Hi ! Thanks for your great work. I'm trying to make the affordance code work with my custom scenes. I tried replicating the .json file that describe the scene mesh...
Hi It is an excellent work for modeling human scene interaction and I have a question about the affordance experiment. As the following code: https://github.com/mohamedhassanmus/POSA/blob/de21b40f22316cfb02ec43021dc5f325547c41ca/src/affordance.py#L264 You save the parameter for...
Hello! This research is fantastic and I want to know about some datasets. I know about PSI datasets. But this project is a little different. 1) data/sdf/MPH112_semantics.npy => Don't you...
Hi, I tried to predict SMPL-X contacts on my own dataset using the trained model provided in the repository, but I got some strange predictions..  The pattern it shows...