Acquiring complete and clean 3D shape and scene data is challenging due to geometric occlusion and insufficient views during 3D capturing. We present a simple yet effective deep learning approach for completing the input noisy and incomplete shapes or scenes. Our network is built upon the octree-based CNNs (O-CNN) with U-Net like structures, which enjoys high computational and memory efficiency and supports to construct a very deep network structure for 3D CNNs. A novel output-guided skip-connection is introduced to the network structure for better preserving the input geometry and learning geometry prior from data effectively. We show that with these simple adaptions -- output-guided skip-connection and deeper O-CNN (up to 70 layers), our network achieves state-of-the-art results in 3D shape completion and semantic scene computation.
@article{arxiv.2006.03762,
title = {Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completion},
author = {Peng-Shuai Wang and Yang Liu and Xin Tong},
journal= {arXiv preprint arXiv:2006.03762},
year = {2020}
}