Orientation field plays the most important role in fingerprint recognition. Proposed in this paper is a novel approach of pixel-wise orientation field estimation using multi-scale Gaussian filter. A three-stage averaging framework in pixel-scale, block-scale, and orientation-scale is developed for handling gradient vectors, coherence data, and orientation vectors, respectively. Experimental results on various FVC datasets show the proposed algorithm achieves accurate orientation field estimation which is robust to local defects, such as scar, low contrast, ridge discontinuity, smudged area, etc. with a low computational cost.