Objectives: This study aims to introduce a novel predictive model for the post-operative facial contours of patients with mandibular defect, addressing limitations in current methodologies that fail to preserve geometric features and lack interpretability.Methods: Utilizing surface mesh theory and deep learning, our model diverges from traditional point cloud approaches by employing surface triangular mesh grids. We extract latent variables using a Mesh Convolutional Restricted Boltzmann Machines (MCRBM) model to generate a three-dimensional deformation field, aiming to enhance geometric information preservation and interpretability.Results: Experimental evaluations of our model demonstrate a prediction accuracy of 91.2 %, which represents a significant improvement over traditional machine learning-based methods.Conclusions: The proposed model offers a promising new tool for pre-operative planning in oral and maxillofacial surgery. It significantly enhances the accuracy of post-operative facial contour predictions for mandibular defect reconstructions, providing substantial advancements over previous approaches.