Rescan: Inductive Instance Segmentation for Indoor RGBD Scans

  title={Rescan: Inductive Instance Segmentation for Indoor RGBD Scans},
  author={Maciej Halber and Yifei Shi and K. Xu and T. Funkhouser},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
In depth-sensing applications ranging from home robotics to AR/VR, it will be common to acquire 3D scans of interior spaces repeatedly at sparse time intervals (e.g., as part of regular daily use). We propose an algorithm that analyzes these ``rescans'' to infer a temporal model of a scene with semantic instance information. Our algorithm operates inductively by using the temporal model resulting from past observations to infer an instance segmentation of a new scan, which is then used to… Expand
5 Citations
Accurate Dynamic SLAM using CRF-based Long-term Consistency.
  • PDF
MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization
  • PDF
Describing and Localizing Multiple Changes with Transformers
  • Yue Qiu, Shintaro Yamamoto, +4 authors Y. Satoh
  • Computer Science
  • ArXiv
  • 2021
  • PDF


ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes
  • 804
  • PDF
3D Semantic Segmentation with Submanifold Sparse Convolutional Networks
  • 297
  • Highly Influential
  • PDF
TSDF-based change detection for consistent long-term dense reconstruction and dynamic object discovery
  • 11
  • PDF
Matterport3D: Learning from RGB-D Data in Indoor Environments
  • 465
  • PDF
Unsupervised learning of spatial-temporal models of objects in a long-term autonomy scenario
  • 21
  • PDF
SceneNN: A Scene Meshes Dataset with aNNotations
  • 147
  • PDF
Meta-rooms: Building and maintaining long term spatial models in a dynamic world
  • 59
  • PDF
LSD-SLAM: Large-Scale Direct Monocular SLAM
  • 2,213
  • PDF
Proactive 3D scanning of inaccessible parts
  • 22
  • PDF
Space-Time Localization and Mapping
  • 2
  • PDF