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
720 stars 128 forks source link

joint coordinate loss question #42

Closed asw91666 closed 3 years ago

asw91666 commented 3 years ago

Hi, thanks for your great work. The paper only says ||P-P*|| (8), but at the code, you used both GT joint coordinate and SMPL joint coordinate for predicting joint. so would you let me know why you use SMPL joint coordinate? Is GT joint an unreliable data? thanks you.

https://github.com/mks0601/I2L-MeshNet_RELEASE/blob/c940da098f42934e5726ec044d2960a4cd9ed141/main/model.py#L91

mks0601 commented 3 years ago

The reason is that in-the-wild datasets, such as MSCOCO, do not provide 3D GT. SMPL joint coordinates are pseudo-GT 3D coordinates, so I'm using it.

asw91666 commented 3 years ago

I see. thank you for quick reply !