Handheld, Automotive
ViViD++
Robust visual SLAM under illumination changes
Repeated handheld and driving recordings combine RGB, thermal and event vision with inertial measurements, depth or LiDAR and scoped reference trajectories.
Access links
Primary places to inspect, download, read about, or reproduce the dataset.
Quick facts
- Vehicle type
- Handheld, Automotive
- Environment
- Indoor, Outdoor
- Data origin
- Real-world
- Sensor count
- 13
- Ground truth
- Available
- Calibration
- Parameters Only
- Annotations
- Not reported
Sensor overview
High-level sensor availability before the detailed sensor records below.
Ground truth
Reference scope, method, rate, coverage, and provenance.
| Scope | Method | Reference system | Count | Rate | Coverage |
Reference provenance
|
|---|---|---|---|---|---|---|
| 6DoF | Motion capture | Not reported | 12 cameras | Not reported | Partial · Handheld Indoor |
Reference provenance
External
|
|
||||||
| Not reported | RTK GNSS | Not reported | Not reported | Not reported | Partial · Driving |
Reference provenance
External
|
|
||||||
| Not reported | LiDAR SLAM | Not reported | Not reported | Not reported | Partial · Handheld Outdoor |
Reference provenance
Derived
|
|
||||||
Calibration and synchronization
Reported calibration level, reproducibility signals, and supporting notes.
- Level
- Parameters Only
- Processed parameters
- Available
- Raw calibration data
- Not reported
- Calibration targets
- Checkerboard, AprilTag grid, heated aluminum-coated PCB, orthogonal planes
Parameters only
Processed calibration parameters are reported, but raw calibration data is not reported.
Notes
Relative-pose chains connect to RGB(-D), excluding onboard IMUs. Kalibr calibrates external IMU; E2VID supplies DVXplorer calibration images; ICP/plane alignment calibrates LiDAR; hand-eye calibration links motion-capture markers.
Known or intentional limitations
Reported constraints and characteristics to check before using the dataset.
Direct lights can cause event artifacts and loss of nearby visual information.
Reference provenance varies by subset: indoor motion capture, outdoor handheld derived baseline, driving RTK position.
Vision-only driving sequences do not provide LiDAR.
Cameras
thermal
- Model
- FLIR A65
- Setup
- Mono
- Count
- 1
- Effective cameras
- 1
- Modality
- Thermal
- Resolution
- 640 x 512
- Rate
- Not reported
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- 69 deg
- VFOV
- 90 deg
- Notes
- Used in both rigs; Table II reports 30 Hz / 20 Hz (handheld). Raw 16-bit container has 14 meaningful bits; manual NUC is performed at sequence start. FOV retained exactly as printed.
handheld-rgbd
- Model
- Asus Xtion Pro Live
- Setup
- Rgbd
- Count
- 1
- Effective cameras
- 2
- Modality
- Rgbd
- Resolution
- 640 x 480
- Rate
- 30 Hz
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- 58 deg
- VFOV
- 45 deg
- Notes
- Handheld RGB/depth system. Structured-light outdoor depth is unreliable; outdoor geometry uses LiDAR.
driving-rgb
- Model
- Flea3 FL3-U3-13E4C-C
- Setup
- Mono
- Count
- 1
- Effective cameras
- 1
- Modality
- Rgb
- Resolution
- 1280 x 1024
- Rate
- 60 Hz
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- 73.8 deg
- VFOV
- 89 deg
handheld-event
- Model
- DAVIS 240C
- Setup
- Mono
- Count
- 1
- Effective cameras
- 1
- Modality
- Event
- Resolution
- 240 x 180
- Rate
- Not reported
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- Not reported
- VFOV
- Not reported
- Notes
- Handheld event sensor also produces intensity images; listed up-to-12-MEPS capacity is not a released frame rate. IR cut filter mitigates motion-capture strobe interference.
driving-event
- Model
- DVXplorer
- Setup
- Mono
- Count
- 1
- Effective cameras
- 1
- Modality
- Event
- Resolution
- 640 x 480
- Rate
- Not reported
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- Not reported
- VFOV
- Not reported
- Notes
- Driving event sensor has no native intensity images; listed up-to-165-MEPS capacity is not a frame rate. E2VID reconstructed images are used for calibration.
IMUs
External handheld IMU
- Model
- LORD Microstrain 3DM-GX5-25
- Count
- 1
- Accel / gyro
- Not reported
MPU 6150
- Model
- MPU 6150
- Count
- 1
- Accel / gyro
- Not reported
MPU 9250
- Model
- MPU 9250
- Count
- 1
- Accel / gyro
- Not reported
Ouster onboard IMU
- Model
- InvenSense ICM-20948
- Count
- 1
- Accel / gyro
- Not reported
GNSS
NovAtel Pwrpak7 E-1
- Model or name
- NovAtel Pwrpak7 E-1
- Count
- 1
- Rate
- Not reported
- GNSS type
- RTK
- Position output
- Available
- Velocity output
- Not reported
- Heading output
- Not reported
LiDAR
Velodyne VLP-16
- Model or name
- Velodyne VLP-16
- Count
- 1
- Dimensions
- Not reported
- Rate
- Not reported
- Channels
- 16
- Range
- 100 m
Ouster OS1-64
- Model or name
- Ouster OS1-64
- Count
- 1
- Dimensions
- Not reported
- Rate
- Not reported
- Channels
- 64
- Range
- 120 m
Radar
Not reported
Pitot tube
Not reported
Additional sensors
Not reported
Annotations
Reported annotation availability and task support.
- Availability
- Not reported
- Format
- Not reported
- Class count
- Not reported
Semantic segmentation
Not reported
Instance segmentation
Not reported
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{lee2022vivid,
title={ViViD++: Vision for Visibility Dataset},
author={Lee, Alex Junho and Cho, Younggun and Shin, Young-sik and Kim, Ayoung and Myung, Hyun},
year={2022},
eprint={2204.06183},
archivePrefix={arXiv},
primaryClass={cs.RO},
url={https://arxiv.org/abs/2204.06183v2}
}
Dataset corrections
Notice a specific issue after reviewing the page?
Report an inaccuracy