Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completion

2020/06/06 by Wang, Peng-Shuai, Liu, Yang, Tong, Xin · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Graphics (cs.GR)

paper · doi:10.48550/arxiv.2006.03762

Abstract

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.

Cited by

• RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion

Related

• O-CNN
• Octree Generating Networks: Efficient Convolutional Architectures for\n High-resolution 3D Outputs
• High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference
• Deep Learned Full-3D Object Completion from Single View
• OctNet: Learning Deep 3D Representations at High Resolutions