LMSCNet: Lightweight Multiscale 3D Semantic Completion
Authors:
- 1 November 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 111-119
Abstract
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 suchit 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.Keywords
All Related Versions
This publication has 34 references indexed in Scilit:
- Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis2017
- Multi-view 3D Object Detection Network for Autonomous Driving2017
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- Semantic Scene Completion from a Single Depth Image2017
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- Structured Prediction of Unobserved Voxels from a Single Depth Image2016
- A Survey of Surface Reconstruction from Point CloudsComputer Graphics Forum, 2016
- Joint 3D Object and Layout Inference from a Single RGB-D Image2015
- Reinforcement learning in robotics: A surveyThe International Journal of Robotics Research, 2013
- A volumetric method for building complex models from range images1996