Comment by Markus for The openni driver does this already. It doesn't just produce one depth image. Check here and here. image_raw contains the raw uint16 depths in mm from the kinect. image contains float depths in m. And finally image_rect also contains float depths in m, but is rectified like you want. The driver even publishes points, a point cloud that puts all the coordinates together for you. If you really need to know the formula, maybe just look at the code in the driver.

Well if I subscribe to /camera/depth/image_rect I just get values from 0 - 255 and no floats .... --> Do I have to read in that data in a particular way? cv_bridge::CvImageConstPtr cv_ptr; cv_ptr = cv_bridge::toCvShare(current_image_); cv::convertScaleAbs(cv_ptr->image, mono8_img, 100,0.0);