The paper introduces TFA, a training‑free aggregation technique that calibrates frozen visual foundation models for visual place recognition. TFA uses cross‑codebook agreement, retrieval coverage, and spectral statistics to adjust residual assignment, spectral shaping, and global‑feature fusion without requiring place labels or task‑specific weights. Experiments with a DINOv2‑B backbone show significant Recall@1 gains over existing training‑free methods across multiple benchmarks, demonstrating that reliability‑guided aggregation can unlock additional retrieval performance from frozen representations.
By Xin Li, Zhimin Mao, Shang Wang, Siyuan Duan, Geng Zhang
Frozen visual foundation models provide transferable features for visual place recognition, but fixed aggregation can suppress useful distinctions in new environments. We introduce TFA, a reliability-...
Deep-learning features excel in visual matching, yet their practical value in tightly coupled visual-inertial SLAM (VI-SLAM) remains insufficiently characterized. We present DL-VINS-Factory, a unified framework that integrates learned feature extractors (ALIKED, RaCo, SuperPoint, XFeat) with either Lucas--Kanade (LK) optical-flow tracking or LightGlue (LG) descriptor matching.
arXiv:2603.25175v2 Announce Type: replace
Abstract: Monocular egocentric 3D pose estimation is difficult because severe foreshortening, self-occlusion, and a restricted field of view often remove the...
By Md Mushfiqur Azam, John Quarles, Kevin Desai
arXiv:2608. 19536v1 Announce Type: cross Abstract: Learning-based global point cloud registration has achieved remarkable progress, yet its reliance on geometric representations makes existing methods sensitive to variations in point density, scan pattern, viewpoint, and sensor characteristics.
By Eunsoo Im, Junghun Suh, Gyeonggwan Lee, Seunghwan Hong
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.
By Adam D. Hines, Michael Milford, Tobias Fischer
SlugTrails is a new egocentric benchmark for floor‑plan‑based indoor visual localization in large buildings, featuring 30 Hz Aria glasses recordings across three campus buildings and six floors (22 089 m²). The dataset includes CAD‑derived floor plans with semantic classes, circulation masks, and laser‑surveyed anchors, and supports three realistic sensing protocols: single walking frames, stationary multi‑view sweeps, and walking streams with odometry. Evaluation of five geometric and learned systems shows that stock models perform poorly, but fine‑tuning on SlugTrails significantly improves performance and cross‑dataset generalization, indicating that data scarcity limits current localization methods.
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.
By Preeti Chatterjee, Jin Lu, Jin Sun, Suchendra M. Bhandarkar
arXiv:2607.20116v2 Announce Type: replace
Abstract: Global visual localization of unmanned aerial vehicles (UAVs) using remote-sensing reference maps has attracted increasing attention. However, diff...
By Xin Li, Siyuan Duan, Shang Wang, Zhimin Mao, Bingliang Hu, Geng Zhang
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...
arXiv:2504.15776v2 Announce Type: replace
Abstract: Public autonomous driving datasets underpin the training and benchmarking of perception, mapping, and localization algorithms, yet residual inaccur...
By Quentin Herau, Nathan Piasco, Moussab Bennehar, Luis Rold\~ao, Dzmitry Tsishkou, Bingbing Liu, Cyrille Migniot, Pascal Vasseur, C\'edric Demonceaux
arXiv:2610.00878v1 Announce Type: cross
Abstract: General-purpose embodied robots should support both navigation toward language-specified destinations and dynamic person tracking under arbitrary ini...
By Pengfei Qi, Haoran Lin, Sizhuang Chen, Kai Luo, Sirui Zhang, Xinqi Liu, Fei Cheng, Wenrui Chen, Liming Yin, Kailun Yang