REVIEW 13 cited by
OKVIS2: Realtime Scalable Visual-Inertial SLAM with Loop Closure
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
OKVIS2: Realtime Scalable Visual-Inertial SLAM with Loop Closure
read the original abstract
Robust and accurate state estimation remains a challenge in robotics, Augmented, and Virtual Reality (AR/VR), even as Visual-Inertial Simultaneous Localisation and Mapping (VI-SLAM) getting commoditised. Here, a full VI-SLAM system is introduced that particularly addresses challenges around long as well as repeated loop-closures. A series of experiments reveals that it achieves and in part outperforms what state-of-the-art open-source systems achieve. At the core of the algorithm sits the creation of pose-graph edges through marginalisation of common observations, which can fluidly be turned back into landmarks and observations upon loop-closure. The scheme contains a realtime estimator optimising a bounded-size factor graph consisting of observations, IMU pre-integral error terms, and pose-graph edges -- and it allows for optimisation of larger loops re-using the same factor-graph asynchronously when needed.
Forward citations
Cited by 13 Pith papers
-
LAMP: Localization Aware Multi-camera People Tracking in Metric 3D World
LAMP tracks 3D human motion from moving multi-camera headsets by converting 2D detections to a unified metric 3D world frame via device localization and fitting with an end-to-end spatio-temporal transformer.
-
Event-based SLAM Benchmark for High-Speed Maneuvers
EvSLAM is a new benchmark for event-based state estimation that exposes limitations in current methods and datasets for high-speed 6-DoF maneuvers using diverse platforms, extreme lighting, and a custom evaluation metric.
-
An RTK-SLAM Dataset for Absolute Accuracy Evaluation in GNSS-Degraded Environments
New RTK-SLAM dataset with independent total-station ground truth demonstrates that SE(3)-aligned ATE underestimates absolute errors by up to 76%, while RTK-SLAM systems achieve centimeter-level accuracy outdoors and d...
-
GrandTour: A Legged Robotics Dataset in the Wild for Multi-Modal Perception and State Estimation
GrandTour releases 49 multi-modal legged-robot missions (>10 km, >5 h) with LiDAR, camera, IMU, depth, proprioception, and mm-level RTK-GNSS/total-station ground truth, plus a 52-method state-estimation benchmark.
-
VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion
VidMap recovers more accurate metric poses and calibration from long unconstrained videos than SOTA SLAM and SfM by treating temporal order as first-class and injecting metric depth into global optimization.
-
VOCA: Visual Odometry with Codec Awareness
VOCA is a causal stereo visual odometry system that achieves state-of-the-art performance on compressed streams by exploiting codec awareness.
-
HumanHalo -- Safe and Efficient 3D Navigation Among Humans via Minimally Conservative MPC
The paper contributes a linear MPC safety constraint that, for the first control input alone, prevents the drone's future reachable set from ever being fully inside a human's reachable set, avoiding inevitable collisions.
-
GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting
A per-scene fine-tuned latent diffusion model with dual mesh-3DGS conditioning and random mask augmentation improves novel-view repair in Gaussian Splatting, outperforming DIFIX baselines on ScanNet++ and Replica.
-
Does Robust VIO Need More Learning? Geometry-Verified Visual Measurements under Distribution Shift
Restricting learning to stereo correspondence and uncertainty, with geometric verification and covariance weighting in an explicit VIO backend, improves OOD trajectory accuracy and success rate over classical and lear...
-
Cross-Spectral Stereo Inertial Odometry
Presents an asynchronous cross-spectral VTI odometry pipeline with spectral-aware weighting and NUC handling that claims better accuracy and robustness than standard stereo VIO.
-
DigiForest: Digital Analytics and Robotics for Sustainable Forestry
DigiForest integrates heterogeneous autonomous robots for data collection, automated tree trait extraction, a decision support system for growth forecasting, and autonomous harvesters for selective logging, with real-...
-
SMF-VO: Direct Ego-Motion Estimation via Sparse Motion Fields
SMF-VO estimates a camera's velocity directly from sparse optical flow with a ray-based motion-field equation, reporting >100 FPS on a Raspberry Pi with competitive visual-odometry accuracy.
-
The Monado SLAM Dataset for Egocentric Visual-Inertial Tracking
The Monado SLAM dataset supplies real egocentric visual-inertial sequences from VR headsets to fill gaps in existing VIO/SLAM benchmarks for difficult real-world scenarios.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.