namepllet
namepllet
Just for convenience. I think the performance will not much different since the average hand pose is constant offset. The average hand pose is not for original dataset(HO3D). It is...
Yes we retrain the Pose2Mesh using HO3D dataset.
We trained our model using 4 2080Ti and it takes ~10 hours. In our experiments, mean joint error are same at 70 and 80 epochs and other metrics are slightly...
I cannot understand the question. What is the transformation between wrist and camera coordinate system ?
The pose[0:3] represent transformation from MANO coordinate system to camera coordinate system.
I select the 'input.png' from MSCOCO validation set and I trained the model with MSCOCO trainset. Since I trained the model with limited data, the model may not generalize well....
You can evaluate the result of HO3D in [codalab challenge](https://competitions.codalab.org/competitions/22485)
I trained the model with MSCOCO trainset. Thanks.
Our training code has some randomness. So please use the pretrained checkpoint for the evaluation.
Yes we obtained the results after procrustes alignment.