Compositional and Scalable Object SLAM

We present a fast, scalable, and accurate Simultaneous Localization and Mapping (SLAM) system that represents indoor scenes as a graph of objects. Leveraging the observation that artificial environments are structured and occupied by recognizable objects, we show that a compositional and scalable object mapping formulation is amenable to a robust SLAM solution for drift-free large-scale indoor reconstruction. To achieve this, we propose a novel semantically assisted data association strategy that results in unambiguous persistent object landmarks and a 2. 5D compositional rendering method that enables reliable frame-to-model RGB-D tracking. Consequently, we deliver an optimized online implementation that can run at near frame rate with a single graphics card, and provide a comprehensive evaluation against state-of-the-art baselines. An open-source implementation will be provided at https://github.com/rpl-cmu/object-slam.

Authors

• Akash Sharma
• Wei Dong
• Michael Kaess

Keywords

• Graphics
• Simultaneous localization and mapping
• Automation
• Conferences
• Rendering (computer graphics)
• Reliability
• Open source software
• Scalable Object
• Deep Neural Network
• Feature Maps
• Object Detection
• Point Cloud
• Semantic Segmentation
• Small Objects
• Coordinate Frame
• Current Frame
• Objects In The Scene
• Instance Segmentation
• Camera Pose
• Object Instances
• Relative Pose
• Object Volume
• Object Pose
• Object Reconstruction
• Semantic Understanding
• Factor Graph
• Deep Object Detection
• Normal Map
• Reprojection Error
• MS COCO Dataset
• Dense Reconstruction
• Separate Thread
• Camera Object
• Voxel Grid
• Intersection Over Union
• Color Map