Abstract: Ground elevation estimation is vital for numerous applications in autonomous vehicles and intelligent robotics including 3D object detection, navigable space detection, point cloud matching for localization and registration for mapping. However, most works regard the ground as a plane without height information, which causes inaccurate manipulation in these applications. Therefore, in this work, we propose GeeNet, a novel end-to-end, lightweight method that completes the ground in nearly real-time and simultaneously estimates the ground elevation in a grid-based representation. GeeNet leverages the mixing of 2D/3D convolutions to preserve lightweight architecture to regress ground elevation information for each cell of the grid. For the first time, GeeNet fulfills ground elevation estimation from semantic scene completion. We utilize the SemanticKITTI and SemanticPOSS datasets to validate the proposed GeeNet. It is demonstrated the qualitative and quantitative performance of GeeNet on ground elevation estimation and semantic scene completion of the point cloud. Moreover, the cross-dataset generalization capability of GeeNet is also experimentally proven. GeeNet achieves state-of-the-art performance and fulfills a run-time of 220 Hz for ground elevation estimation and ground completion.