Skip to content
Siddhant Shrivastava
LettersResearchDiaryPapersTalksCoursesExplainersAbout

Research diary

Home

❯

Entities

❯

datasets

❯

ScanNet

ScanNet

16 Oct 20261 min read

  • entity

RGB-D video of indoor rooms with 3D reconstructions and semantic labels, about 1,500 scans (Dai and others, 2017). The default indoor test set for 3D scene understanding, and so for most scene graph papers.

Website

Mentioned in

8 papers:

  • 3DSG survey (2026)
  • vS-Graphs (2026)
  • Mono-Hydra++ (2026)
  • SuperMap (2026)
  • Open3DSG (2024)
  • HOV-SG (2024)
  • Mono-Hydra (2023)
  • 3-D Scene Graph (Kim) (2019)

Graph View

Backlinks

  • Catalogue
  • Entities
  • Mapping and localisation
  • Semantic mapping
  • 3-D Scene Graph: A Sparse and Semantic Representation of Physical Environments for Intelligent Agents
  • Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships
  • 3D Scene Graphs: Open Challenges and Future Directions
  • vS-Graphs: Tightly Coupling Visual SLAM and 3D Scene Graphs Exploiting Hierarchical Scene Understanding
  • Mono-hydra: Real-time 3D scene graph construction from monocular camera input with IMU
  • Mono-Hydra++: Real-Time Monocular Scene Graph Construction with Multi-Task Learning for 3D Indoor Mapping
  • Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation
  • SuperMap: A Spatio-Temporal SLAM System for Visual-Language Navigation

Created with Quartz v5.0.0 © 2026

  • Home
  • Letters
  • Papers
  • Explainers
  • Feeds