I don't know what is going on. I just try to test python -m pyk4a.viewer --undistort_depth --vis_depth --parallel_bt I have connected my Kinect Camera. But it still can not run. The Bugs look like these:

1. When I ran the ./run_server.sh, there was no windows/plots displayed.
2. I also receive an issue: "tjDestroy error"

I was wondering if any suggestion to resolve the above issues? Here is the screenshot:

BTW, when I tested "python -m pyk4a.viewer --vis_color --no_bt --no_depth", there was a window that shows the RGB stream captured by Kinect.

Thank you!

Hi Renat,

I was trying to obtain the SMPLX parameters and convert them to an SMPL mesh. The only difference is that I lose the hand pose information and thus I just set the last 6 axis angle parameters in the SMPL body pose as zero. But it turns out there is a consistent shift along the y-axis. I attached the SMPL and SMPLX point cloud in this drive link https://drive.google.com/drive/folders/1JsmK6dNOJfsDImfuqyESp5sQdwilKhGU?usp=sharing.

I extract the intermediate results by inserting the following code in the file aggregate.py before visualization and run the standard SMPL model forward function to get the SMPL vertices. BTW, I disabled the prediction for hand and face pose, but I don't think that can result in my current issue. This seems to relate to the global translation. But it should not differ between SMPL and SMPLX. Do you maybe have any idea why this happened? Many thanks in advance!

          smpl_dict['body_pose'] = x['body_pose']
          smpl_dict['global_rot'] = x['global_rot']
          smpl_dict['global_trans'] = x['global_trans']
          smpl_dict['smplx_verts'] = vertices.detach().cpu().numpy().squeeze()
          import pickle as pkl
          pkl.dump(smpl_dict, open('extract_from_raw.pkl', 'wb'))

Hi, @rmbashirov, Thanks a lot for publishing this code and really interesting paper. As I am quite new to use the docker to build and run the examples.

• According to your README.md, I have installed the docker and nvidia-docker and build the images like:
• I attached my azure camera to computer (I also check by running k4aviewer with success)
• After change some information in run_local.sh and data_dirpath in renet.yaml, I run the sudo ./run_server.sh , but it gives me this:

docker: Error response from daemon: OCI runtime create failed: container_linux.go:367: starting container process caused: exec: "python": executable file not found in $PATH: unknown

it seems that there is no python

Computer infor:

• Ubuntu 18.04
• NVIDIA Geforce 1080Ti

Dear Sir: If I want to use my Kinect ONE (Kinect2)camera to get the image instead of Kinect Azure, how can I modify the code? In what codes? Could you please give me some hints? Thanks Li

Thanks for your great work. I download the docker from Google Drive. Failed to run pyk4a.viewer

~/humanReconstruct/rgbd-kinect-pose/docker$ ./run_local.sh docker@txt-Lab:/src$ python -m pyk4a.viewer --vis_color --no_bt --no_depth Traceback (most recent call last): File "/opt/conda/lib/python3.7/runpy.py", line 183, in _run_module_as_main mod_name, mod_spec, code = _get_module_details(mod_name, _Error) File "/opt/conda/lib/python3.7/runpy.py", line 109, in _get_module_details import(pkg_name) File "/opt/conda/lib/python3.7/site-packages/pyk4a/init.py", line 2, in from .pyk4a import * File "/opt/conda/lib/python3.7/site-packages/pyk4a/pyk4a.py", line 3, in import k4a_module ImportError: libopencv_core.so.4.2: cannot open shared object file: No such file or directory

any advice?

Hi Can you pleas share your code for what you call in the paper ’SMPLify-RGBD’ - a single view modification of the offline model fitting. I would like to use it to create a reference solution using a Real Sense RGBD camera.

Thanks, David

Thank you @rmbashirov for open sourcing this piece of art. Can we use this for RGB-D data from other sources like iPhone TrueDepth or other sources? If this can be done, where shall we provide the camera intrinsic?

...... E: Unable to locate package libcudnn7 E: Unable to locate package libcudnn7-dev The command '/bin/sh -c apt-get -y update && apt-get install -y --no-install-recommends libcudnn7=7.6.5.32-1+cuda10.2 libcudnn7-dev=7.6.5.32-1+cuda10.2 && apt-mark hold libcudnn7 && rm -rf /var/lib/apt/lists/*' returned a non-zero code: 100

Hi @rmbashirov,

Thanks for your support on this repo! It's very interesting project.

I believe my issue may be related to #5.

I have downloaded the docker image from google drive link and I'm attempting to test the kinect viewer. I'm receiving the following error.

I completed the steps indicated by @xgen in #5 to expose all GPU's in the call to ./run_local.sh.

My GPU is listed when calling nvidia-smi inside docker, however I notice the CUDA version is 11.6, not 10.2.

Any ideas?

Hello,

I am interested in using this model for a research study, however, I am unable to run this model in real-time as I'm using a cluster for computation. Is it possible to use this model not in real-time e.g. by providing depth maps and video files, or by providing previously captured keypoints from azure skeletal tracking, minimalhand and mediapipe?

Any advice on this would be greatly appreciated.

@rmbashirov hello,Thank you for sharing this project. I made the following mistakes in the implementation process. Can you help me see what the problem is?