We introduce a new approach for multiscale 3Dsemantic scene completion from voxelized sparse 3D LiDAR scans. As opposed to the literature, we use a 2D UNet backbone with comprehensive multiscale skip connections to enhance feature flow, along with 3D segmentation heads. On the SemanticKITTI benchmark, our method performs on par on semantic completion and better on occupancy completion than all other published methods -- while being significantly lighter and faster. As such it provides a great performance/speed trade-off for mobile-robotics applications. The ablation studies demonstrate our method is robust to lower density inputs, and that it enables very high speed semantic completion at the coarsest level. Our code is available at https://github.com/cv-rits/LMSCNet.
@article{arxiv.2008.10559,
title = {LMSCNet: Lightweight Multiscale 3D Semantic Completion},
author = {Luis Roldão and Raoul de Charette and Anne Verroust-Blondet},
journal= {arXiv preprint arXiv:2008.10559},
year = {2020}
}
Comments
Accepted at 3DV 2020 (Oral). For a demo video, see http://tiny.cc/lmscnet. Code is available at https://github.com/cv-rits/LMSCNet