VIBE
VIBE copied to clipboard
mkocabas
Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"
I do some traing, one of train log: 2021-04-12 05:53:50,174 GPU name -> GeForce GTX 1070 2021-04-12 05:53:50,174 GPU feat -> _CudaDeviceProperties(name='GeForce GTX 1070', major=6, minor=1, total_memory=8117MB, multi_processor_count=15) 2021-04-12 05:53:50,174...
Hello, unfortunately, I am still not able to reproduce the results published in the paper. According to #98 and #69, this is an issue not only for me but also...
generated character animation has obvious jitter, how can I smooth the action, thank you
1. operating system and the version: ubuntu18 2. python version: 3.6 3. pytorch version: 1.6 Did anyone else have the same problem? The accuracy is decreasing, and the error is...
In fbx_output.py, root translation is passed to Blender via the 'trans' array. In the other hand, this array is a constant. see line 167 : trans = np.zeros((poses.shape[0], 3)) is...
Hi, thanks for sharing your great work. However, I think it would be nice of you to provide a proper training code for the reproducibility. As you know, the Mosh...
I found that, the input images are firstly passed into SPIN feature extractor. The extracted features are then used in VIBE training. I wonder if you have ever tried merging...
Hello! Thanks again for the amazing work! I still have one question regarding the SPIN skeleton model you use in preprocessing. For exemple for the MPI-INF-3DHP dataset, preprocessed in https://github.com/mkocabas/VIBE/blob/master/lib/data_utils/mpii3d_utils.py...
Why keep stopping here? Running VIBE on each tracklet... 0%|
