Training with custom dataset

mks0601 / V2V-PoseNet_RELEASE

Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018

https://arxiv.org/abs/1711.07399

MIT License

377 stars 69 forks source link

Training with custom dataset #21

Closed konrad-marzec closed 6 years ago

konrad-marzec commented 6 years ago

Hi, I have created my own custom dataset. I have disparity maps and want to finetune V2V-posenet. Can you explain what the following values are ? How you get them from presented datasets ?

fx = 241.42
fy = 241.42
cubicSz = 200

minDepth = 100
maxDepth = 700

mks0601 commented 6 years ago

Hi.

fx, fy are focal length of the camera in mm. cubicSz is the length of one edge of a cubic to crop a hand in the 3D space. minDepth and maxDepth are some kind of heuristic parameter to localize the center-of-mass of the hand.

konrad-marzec commented 6 years ago

thanks :)