A time-of-flight camera provides depth maps of the scene at video frame rate. However, their depth measurements are severely influenced by random noise and systematic bias. Previous approaches on depth denoising are usually variants of adaptive joint bilateral filtering with the help of a color image of the same scene. In this paper, we access to the raw range measurements of the ToF sensor instead of the transformed depth values, and we acquire range error profile for each pixel along the range measurement by capturing a planar scene at different distances. We correct the range bias using plane fitting and then the remaining noise can be assumed to follow a zero-mean Gaussian distribution with variance according to the pixel location and the range measurement. Since the whole process is done beforehand leaving variance information, any kind of depth denoising algorithm assuming zero-mean Gaussian noise can perform well with our noise estimation.