ClearGrasp is a method for estimating the 3D geometry of transparent objects from a single RGB-D image using a CNN architecture. It creates both synthetic and real datasets of transparent objects with surface normals, segmentation masks and depth information. The CNN takes an RGB image as input and outputs the surface normals, segmentation masks and occlusion boundaries. A global optimization method is then used to estimate depth from these outputs. The method achieves accurate 3D shape estimation and enables improved robot grasping of transparent objects compared to without using ClearGrasp.