VIBE icon indicating copy to clipboard operation
VIBE copied to clipboard

Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

Results 125 VIBE issues
Sort by recently updated
recently updated
newest added

1.when i run in my pc,it will be ok,but i choose to run it in floydhub,the renderer will be false like that: ![image](https://user-images.githubusercontent.com/81757380/122200450-a3ffcd00-cecd-11eb-80dc-a11a15c5c0cf.png) ,but it will be wrong : ![image](https://user-images.githubusercontent.com/81757380/122200746-e88b6880-cecd-11eb-9473-191ff2bc77f5.png)...

bug

Thanks again for your great work. But I found **two critical bugs**. 1. While the paper says VIBE uses a bi-directional GRU, the code and pre-trained model weights you provide...

bug

I want to analyze the video data of the camera in real time.Then How do I revise the demo.py to fit this mission?

enhancement

Thank you for your work. I follow the windows tutorial. But when I run **install_conda.bat** this step There is a error: ERROR: Command errored out with exit status 128: git...

bug

Enable live Inferencing from webcam. For fast performance program stores result of mpt and hmr of last few frames and combines them with that of latest frame and feeds them...

My operation system is Windows 10, and my GPU driver is GeForce Game Ready Driver. I got this error below, could you give me some hints, what's this error talking...

bug

python demo.py --vid_file sample_video.mp4 --output_folder output/ --display Running "ffmpeg -i sample_video.mp4 -f image2 -v error /tmp\sample_video_mp4/%06d.png" Traceback (most recent call last): File "demo.py", line 383, in main(args) File "demo.py", line...

bug

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] orig_width=640 orig_height =640 renderer...

enhancement

``` (vibe-env) mona@mona:~/research/VIBE$ pip install -r requirements.txt Requirement already satisfied: numpy==1.17.5 in /home/mona/anaconda3/envs/vibe-env/lib/python3.7/site-packages (from -r requirements.txt (line 4)) (1.17.5) Requirement already satisfied: torchvision==0.5.0 in /home/mona/anaconda3/envs/vibe-env/lib/python3.7/site-packages (from -r requirements.txt (line 19))...

bug

It seems like the fbx_output.py only use the SMPL default male/female model as the input, and extract vibe pose output to create animations. Is there anyway to create .fbx file...