3DMPPE_POSENET_RELEASE
3DMPPE_POSENET_RELEASE copied to clipboard
mks0601
Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019
Hello It is a wonderf work. I have a question about dataset which may be beyond the scope of your work, If I want to predict 3D coordinate directly from...
Thanks for your wonderful work, but could you share us the origin Human36M dataset ?
Hi, I was redesigning baseline of several blocks and other parameter for my experiment. I'm pretty sure that except for modifying parser, and some parameter(I think I did not changed...
Hi, Wonderful project thank you.How can i run my own img on demo.py? I use my own img shows the same result about your input img.
Hi Thank you for your great work, I am a beginner, I have some questions to ask: 1, this project can run on my Windows10 computer? 2. What if the...
Hi, I would like to ask why I downloaded your Human3.6M images missing part, can provide a complete data set, thank you very much!
After I downloaded the 2.6m dataset, there is no distinction between manual labeling and machine labeling pictures, both are in the train folder, how do I know which one is...
Hello, thanks for your greate job. I have downloaded the Human3.6m from your google drive and I unzip the images. I found that some folder is missed ,such as I...
Hello, I am trying to adapt the MPII_3DHP dataset on your code, but it's totally overfitting First I train it on H36M+MPII，the MPJPE is about 50+. This is normal Then...
Hello, can tell me the file name format s_11_act_13_subact_02_ca_02_002254.jpg, such as s_[name1]_act_[name2]_subact_[name3]_ca_[name4]_[name5], What do these five names mean and what do they include?
