VideoReloc presents a method for long‑term indoor video relocalization that relies on a compact semantic scene graph rather than visual appearance. By adaptively selecting clip lengths based on odometry and object‑motion criteria, the system gathers spatial evidence, verifies poses through object triplets, and refines orientation using box faces and gravity cues. This approach achieves high localization accuracy with a tiny 100 kB map, outperforming traditional appearance‑based methods on RIO10 and ReplicaCAD datasets.
arXiv:2608. 16658v1 Announce Type: cross Abstract: Cross-view Video Geo-localization (CVG) aims to localize ground-view videos by retrieving their corresponding geo-tagged aerial images.
Indoor visual relocalization plays a critical role in emerging spatial and embodied AI applications. However, prior research was predominantly devoted to low-level vision schemes, struggling to perceive scene semantics and compositions, which limits both interpretability and applicability.
arXiv:2609.09396v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) advance toward physical deployment, the focus has remained on action-oriented Embodied AI evaluated on subject-centric...
arXiv:2512. 02473v2 Announce Type: replace-cross Abstract: Video world models have attracted significant attention for their ability to produce high-fidelity future visual observations conditioned on past observations and navigation actions.
Know-Your-Scene (KYS)-SLAM extends ORB‑SLAM3 by replacing binary feature rejection with continuous correspondence modulation based on semantic, panoptic, and motion priors. Each keypoint is augmented with hierarchical compatibility scores that down‑weight features on independently moving objects while preserving static structure, using a training‑free depth‑aware ego‑motion model and self‑calibrating thresholds. Across 21 stereo sequences, KYS‑SLAM achieves a 17.4% ATE RMSE reduction on outdoor KITTI, 27.7% on indoor EuRoC, and significant improvements on dynamic and synthetic datasets without per‑sequence tuning.
The paper presents MegaEvent, an event‑based visual place recognition system that remains robust to viewpoint changes. By converting five large‑scale geo‑tagged datasets into synthetic event streams and fine‑tuning a vision transformer with a multi‑loss function, MegaEvent achieves an average Recall@1 of 82% on three event‑based localization datasets, outperforming existing methods by 20 recall points. The authors also introduce the Springfield‑Event‑VPR dataset, a 3.7 km walking route recorded in three camera orientations, where MegaEvent surpasses the strongest baseline by 9 recall points.
arXiv:2606. 11683v1 Announce Type: cross Abstract: Spatial reasoning from egocentric videos is inherently challenging because the observable evidence is constrained by the camera trajectory.
arXiv:2608.27529v1 Announce Type: new Abstract: Streaming 3D reconstruction from extremely long videos requires estimating camera motion and scene geometry online under bounded memory and computation...
arXiv:2606. 07708v1 Announce Type: cross Abstract: We introduce a dataset and benchmark for cross-view urban traffic perception built from synchronized ego-centric bicycle videos and aerial drone videos recorded at real urban intersections.
Stereo visual SLAM systems built on local descriptors suffer from semantic ambiguity, instance-level confusion, and independently moving objects, each corrupting data association and accumulating as t...
The paper introduces a top‑down framework for accurately locating athletes in metric world coordinates using a single calibrated broadcast frame. It presents three main contributions: a Boundary‑Aware Adaptive Tiling method that expands tile boundaries to avoid splitting athletes across tiles, a specialized two‑keypoint estimator based on RTMPose‑X for pelvis and ground projection points, and a deterministic lift of 2D projections into 3D world coordinates via camera‑calibrated ray casting. The approach achieves a LocSim score of 97.44 and an mAP of 0.9128, surpassing the baseline by over 21 % on a public test set.
arXiv:2608.30657v1 Announce Type: new Abstract: Fixed-viewpoint infrastructure sensors repeatedly observe the same traffic space, making roadside 3D occupancy structurally different from ego-vehicle...