Other
Replica
Reconstructed indoor assets for embodied perception and rendering
Eighteen real-space reconstructions provide HDR textured meshes, semantic instances, planar reflectors and Habitat-ready assets.
Access links
Primary places to inspect, download, read about, or reproduce the dataset.
Quick facts
- Vehicle type
- Other
- Environment
- Indoor
- Data origin
- Real-world
- Sensor count
- 0
- Ground truth
- Not reported
- Calibration
- Not reported
- Annotations
- Available
Sensor overview
High-level sensor availability before the detailed sensor records below.
Ground truth
Reference scope, method, rate, coverage, and provenance.
Not reported
Calibration and synchronization
Reported calibration level, reproducibility signals, and supporting notes.
- Level
- Not reported
- Processed parameters
- Not reported
- Raw calibration data
- Not reported
- Calibration targets
- Not reported
Calibration data
Calibration reproducibility details are not reported.
Notes
The released product is reconstructed scene assets and a rendering SDK; a raw physical sensor-calibration archive is not established.
Known or intentional limitations
Reported constraints and characteristics to check before using the dataset.
Eighteen reconstructed scenes span 35 rooms; six scenes are rearrangements of one apartment. Scene counts are not independent-building counts or recording sequences.
The release contains real captured/reconstructed meshes, textures, reflectors and semantic/navigation assets. Views generated by the SDK or Habitat are synthetic derivatives with configurable cameras.
Raw physical capture-camera and IMU logs are not established as released inputs; no fixed camera inventory, generated-view count or capture cadence is asserted.
Manual surface completion, reflective surfaces and reconstruction artifacts affect geometry. Mesh labels and rendered depth/pose depend on reconstruction and rendering, without independently measured accuracy.
Dataset research terms govern access and use; renderer capabilities and code availability do not make all source assets unrestricted.
Cameras
Not reported
IMUs
Not reported
GNSS
Not reported
LiDAR
Not reported
Radar
Not reported
Additional sensors
Not reported
Annotations
Reported annotation availability and task support.
- Availability
- Available
- Format
- Hierarchical mesh-primitive segmentation forests in JSON/BIN; renderable semantic/instance labels.
- Class count
- 88
Semantic segmentation
Available
Instance segmentation
Available
Object detection
Not reported
Optical flow
Not reported
Depth ground truth
Not reported
Citation
Citation key and BibTeX kept at the end of the page for reference.
@misc{straub2019replica,
author = {{Julian Straub} and {Thomas Whelan} and {Lingni Ma} and {Yufan Chen} and {Erik Wijmans} and {Simon Green} and {Jakob J. Engel} and {Raul Mur-Artal} and {Carl Ren} and {Shobhit Verma} and {Anton Clarkson} and {Mingfei Yan} and {Brian Budge} and {Yajie Yan} and {Xiaqing Pan} and {June Yon} and {Yuyang Zou} and {Kimberly Leon} and {Nigel Carter} and {Jesus Briales} and {Tyler Gillingham} and {Elias Mueggler} and {Luis Pesqueira} and {Manolis Savva} and {Dhruv Batra} and {Hauke M. Strasdat} and {Renzo De Nardi} and {Michael Goesele} and {Steven Lovegrove} and {Richard Newcombe}},
title = {The Replica Dataset: A Digital Replica of Indoor Spaces},
year = {2019},
eprint = {1906.05797},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/1906.05797v1}
}Dataset corrections
Notice a specific issue after reviewing the page?
Report an inaccuracy