Abstract: The reconstruction of 3D terrain geometry from images is essential for compositing CG objects into a live-action background or for 2D to 3D conversion of terrain scenes. We present a novel mesh refinement algorithm for the creation of stereoscopic images of terrain scenes. Previous approaches emphasise the smoothness of the resulting terrain mesh over accuracy 1. Point cloud-based methods cannot effectively recover the entire surface, leading to visual discrepancies after monocular sequences are converted into 3D stereo. As misalignment or inaccurate 3D terrain data over corresponding 2D background images can result in visual fatigue when stereo sequences are generated, ensuring accuracy of the reconstructed geometry is very important. To achieve the necessary accuracy, our method evaluates mesh errors utilising a texture projection onto the geometry and refines the mesh using Laplacian-based editing. Our algorithm automatically generates stereoscopic images of terrain scenes. In addition, our method simplifies identification and compositing of foreground objects on the terrain geometry.