MotionSC: Data Set and Network for Real-Time Semantic Mapping in Dynamic Environments
This work addresses a gap in data for dynamic semantic mapping, which is incremental as it builds on existing 3D deep learning architectures.
The authors tackled the lack of outdoor semantic scene completion data for dynamic environments by creating a novel data set and a real-time mapping algorithm, MotionSC, which quantifies accurate scene completion with dynamic objects, though no concrete numbers are provided.
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.