Background: The purpose of this study was to develop and evaluate a novel elbow arthroscopy system with superimposed bone and nerve visualization based on preoperative computed tomography (CT) and magnetic resonance imaging (MRI) data. Methods: We obtained bone and nerve segmentation data by CT and MRI, respectively, of the elbow of a healthy human volunteer and cadaveric Japanese monkey. A life size 3-dimensional (3D) model of human organs and frame was constructed using a stereo-lithographic 3D printer. Elbow arthroscopy was performed using the elbow of a cadaveric Japanese monkey. The augmented reality (AR) range of error was examined at 1 cm and 2 cm scope–object distances. Results: We successfully performed AR arthroscopy using the life-size 3D elbow model and the elbow of the cadaveric Japanese monkey by making anteromedial and posterior portals. The computer graphics (CG) position and shape were initially different because of lens distortion. The CG position and shape were corrected to match the arthroscopic view using lens distortion parameter estimates based on the calibration pattern. AR position and shape errors were 2.3 mm at 1 cm scope–object distance and 3.6 mm at 2 cm scope–object distance. Conclusion: We attained reasonable accuracy and demonstrated the working of the designed system. Given the multiple applications of AR-enhanced arthroscopic visualization, it has the potential to be the next-generation technology for arthroscopy. This technique will contribute the reduction of serious complications associated with elbow arthroscopy.