In this paper, we address a robust matching technique based on coded structured lighting (SL) to achieve real-time 3-D reconstructions. To that purpose, most existing approaches involve color or grey levels coding but they are well-known to be sensitive to spectral properties and texture of the viewed surfaces. Therefore, the overall robustness of the proposed technique comes first from the geometrical features used in conjunction with the SL neighbourhood scheme to carry out pattern coding. Second, a desired minimum Hamming distance between features' codewords drives the pattern design. This is suited for autonomous navigation in unknown environments as this parameter enables codewords correction capabilities during the decoding stage in real-time. Furthermore, we take advantage of the known epipolar geometry by including projective invariants between corresponding epipolar lines directly in the pattern components. Thus, the final pattern displays relocated and reoriented (cuneiform) features along the epipolar lines. This grouping also contributes to reduce the search space more and results in a significantly less constrained coding. Finally, we show how this coding and this non-grid based pattern offer efficient and fast correction of mislabeled features due to blurring, spectral harmful effects and surfaces discontinuities prior to the 3-D reconstruction of real scenes.