Data description

The dataset contains the following directories:

- Train1: for training single frame pose recovery which contains 16bit raw depth images, segment images labeled from 1 to 25 (0 for background) and txt files for joint locations. The format of the txt file is as follows:

-1 <finger 1 status> <finger 2 status> <finger 3 status> <finger 4 status> <finger 5 status>

0 X Y Z U V


19 X Y Z U V

finger status is a continous number showing how open the finger is. X, Y and Z are 3D joint locations in each axis in blender in meters, and U and V are joint image plane coordinates.

- Train2: for training temporal pose recovery, just contains txt file in the same format as above. In this dataset, global view (or palm joints) is fixed as a reference for all frames. This dataset was recorded with different finger deformations and movement speed.

- Test: for evaluating the algorithm. 


We trained some coefficients to convert 16bit raw depth image to real depth values and a bias to adjust depth values with kinect2 camera as:

a = 1.537713182783716e+03;
b = -1.958992153351393e+02;
c = 5.456122487076314e+02-10;
kinect2 = -160;

dim(pixel_idx) = kinect2 + c + b * dim(pixel_idx) / 65535 + a * (dim(pixel_idx) / 65535) ^ 2; % dim is a depth image

Z = Z * 1000 + kinect2; % 1000 is multiplied to convert to mm


We use kinect2 camera parameters to reconstruct point cloud:

intrinsics=[519.30 0 334.00
    0 516.60 236.00
    0 0 1];


Dataset is available here to download (~6GB).


There are no news registered in Hand pose recovery