Know-Your-Scene (KYS)-SLAM is presented, a modular extension of ORB-SLAM3 that supplants feature rejection with continuous correspondence modulation, and contends that contextual implausibility is better expressed as a graded quantity than an exclusion criterion.
Abstract
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 trajectory drift. Prevailing semantic and dynamic SLAM methods address this through binary feature rejection, sacrificing correspondence density for outlier suppression. We contend that contextual implausibility is better expressed as a graded quantity than an exclusion criterion. We present Know-Your-Scene (KYS)-SLAM, a modular extension of ORB-SLAM3 that supplants feature rejection with continuous correspondence modulation. The contribution is the reframing of contextual evidence as correspondence cost, applied within feature matching and leaving the geometric backend unmodified. Each keypoint is augmented with semantic, panoptic, and motion priors fused through a hierarchical compatibility formulation, in which semantic class and instance identity enforce structural plausibility while a zero-shot motion score down-weights features on independently moving objects. That score comes from a training-free module fitting a depth-aware ego-motion model to background optical flow and classifying panoptic segments via self-calibrating, coverage-aware thresholds, so only segments with sufficient motion evidence are penalized and static structure is left unpenalized. Penalizing correspondences rather than discarding them preserves the geometric support bundle adjustment depends on. Under one fixed configuration, no coefficient retuned per sequence or dataset, KYS-SLAM reduces per-sequence ATE RMSE by 17.4% on outdoor KITTI and 27.7% on indoor EuRoC across 21 stereo sequences with no regressions, and by 6.6% on dynamic subsets of KITTI Tracking and 17.8%, up to 31.2%, on Virtual KITTI 2 -- cross-domain transfer across outdoor driving, indoor flight, and synthetic imagery under one set of constants.
Traditional visual SLAM methods generally rely on the static-scene assumption and may suffer substantial localization degradation in the presence of moving objects. To address this issue, this paper proposes a dynamic visual SLAM method based on semantic and scene-flow constraints and integrates it into the ORB-SLAM3...
Yu-Qian Yan, Guang-Wu Chen, Xin Zhou et al.· Engineering Research Express· 0 citations
Visual simultaneous localization and mapping (SLAM) often degrades in low-light environments because of insufficient brightness, reduced contrast, and loss of texture, which cause sparse features, accumulated mismatches, and unstable trajectories. This paper presents RetiGlue-SLAM, a visual-inertial SLAM framework that...
Yi-Ming Li, Xian-Pu Liang, Guang-Ming Guo et al.· ISPRS International Journal...· 0 citations
Online semantic Gaussian SLAM typically updates three-dimensional semantic maps using frame-wise predictions from two-dimensional semantic segmentation networks. However, occlusions, viewpoint changes, and object boundaries may introduce transient misclassifications, which can further cause cross-frame semantic inconsi...
Chen Dai, Hao-Yu Duanmu, Xu Sun et al.· Italian National Conference...· 0 citations
This work presents BPC-SLAM, an RGB-D SLAM system featuring part-level dynamic suppression and structure-constrained optimization for dynamic human environments, and improves the robustness and accuracy of pose estimation by incorporating human structural constraints.
Jiu-Peng Chen, Wang Yang, H. San et al.· The Visual Computer· 0 citations
Monocular Gaussian SLAM must recover camera motion, surface structure, and appearance from an RGB sequence without metric depth input or benchmark geometry during reconstruction. This setting is challenged by scale-ambiguous predictions, spatially varying reliability, and the tendency of an unconstrained Gaussian map t...