Three-dimensional face recognition has shown its potential to obtain higher recognition accuracy than 2D methods. Among numerous face recognition methods, registration of two faces is comparatively intuitive. We propose a rigid registration method using surface resampling and denoising, which lowers the impact on registration residuals caused by sampling difference and noise, significantly improving the accuracy. While sparsity-inducing norms reduce sensitivity to outliers and missing data, with preprocessing and region segmentation methods, our registration method is applied to face verification. Without data-driven learning or training, only residuals of rigid registration are utilized, and verification rates at 0.1% FAR are as follows: 100% for n versus n, 96.9% for n versus all, and 98.6% for ROC III experiment on FRGC v2.0 database, and 100% for n versus n and 95.7% for n versus all on Bosphorus database. Experiments show that the proposed algorithm outperforms the state-of-the-art algorithms and is preferable in a verification scenario.