search

mks0601 / I2L-MeshNet_RELEASE

Official PyTorch implementation of "I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image", ECCV 2020
MIT License
710 stars 130 forks source link

QuestionsAbout the acquisition of SMPL parameters in the Human3.6M data set #64

Open booker-max opened 3 years ago

booker-max commented 3 years ago

I’m sorry to bother you again. I saw a sentence in your paper "Alternatively, we obtain groundtruth SMPL parameters by applying SMPLify-X on the groundtruth 3D joint coordinates of Human3.6M dataset." time,

Did you use groundtruth?

How are groundtruth 3D joint coordinates used when calculating smpl parameters?

Can you share your code for calculating smpl parameters, thank you very much.

mks0601 commented 3 years ago

I fit SMPL body model to GT 3D pose of Human3.6M using SMPLify-X. Details can be found in Section 13 of my another paper (https://arxiv.org/pdf/2011.11232.pdf).

booker-max commented 3 years ago

Thank you.