MotionSC: Data Set and Network for Real-Time Semantic Mapping in Dynamic Environments

TL;DR

This paper introduces a new outdoor dataset for semantic scene completion in dynamic environments, along with MotionSC, a real-time mapping network leveraging 3D deep learning and temporal data for improved scene understanding.

Contribution

It provides a novel outdoor dataset with dynamic scenes and develops MotionSC, a real-time dense semantic mapping network utilizing recent 3D deep learning architectures.

Findings

The dataset enables accurate supervision of scene completion with dynamic objects.

MotionSC outperforms existing methods in real-time semantic mapping.

The dataset and network improve dynamic scene understanding in outdoor environments.

Abstract

This work addresses a gap in semantic scene completion (SSC) data by creating a novel outdoor data set with accurate and complete dynamic scenes. Our data set is formed from randomly sampled views of the world at each time step, which supervises generalizability to complete scenes without occlusions or traces. We create SSC baselines from state-of-the-art open source networks and construct a benchmark real-time dense local semantic mapping algorithm, MotionSC, by leveraging recent 3D deep learning architectures to enhance SSC with temporal information. Our network shows that the proposed data set can quantify and supervise accurate scene completion in the presence of dynamic objects, which can lead to the development of improved dynamic mapping algorithms. All software is available at https://github.com/UMich-CURLY/3DMapping.