In this study, a super-resolution reconstruction approach for binocular 3D data is proposed. The aim is to obtain the high-resolution (HR) disparity map from a low-resolution (LR) binocular image pair by super-resolution reconstruction. The proposed approach contains five stages, i.e., initial disparity map estimation using local aggregation, disparity plane model computation, global energy cost minimization, HR disparity map composition by region-based fusion (selection), and fused HR disparity map refinement. Based on the experimental results obtained in this study, in terms of PSNR and bad pixel rate (BPR), the final HR disparity maps by the proposed approach are better than those by four comparison approaches.