We propose a framework for face recognition performed in 3D space. A 3D facial model consisting of a sparse depth map is constructed from stereo images using isoluminance lines for the stereo matching. By searching for arcs whose radiuses are of certain ranges, we can locate the candidate irises very efficiently. After the pose of the face is detected, the 3D model is transformed into a canonical pose. Calculating the mean differences in depth between corresponding data points in the test 3D model and all the models in the database performs recognition. By corresponding data points it is meant a pair of closest data points in two 3D models. We show that even without using any 2D features, we can do face recognition depending on the depth information only. The 3D pose-detecting algorithm makes it possible for our face recognition algorithm to be posing invariant.