A large-scale urban semantic mapping dataset featuring realistic city layouts, high-fidelity rendering, and instance-level annotations spanning multiple object scales is introduced and a category-aware likelihood calibration policy is proposed that identifies and alleviates unreliable observations according to object category and viewing distance.
Abstract
Semantic mapping is fundamental to embodied navigation, yet existing methods are developed for indoor environments, where objects exhibit relatively limited scale variation and are observed from a restricted range of viewpoints. Urban environments pose substantially greater challenges: agents must map objects ranging from pedestrians to buildings while navigating large spaces with highly diverse viewing distances. These conditions introduce two key difficulties that existing datasets and methods fail to cover. First, object scale and observation distance can be severely mismatched. For example, small objects may be viewed from far away, whereas large objects may be observed at extremely close range, resulting in unreliable observation likelihoods. Second, objects with substantially different sizes and geometries require distinct mapping behaviors, which are difficult to capture with a single shared value estimator. To investigate these challenges, we introduce a large-scale urban semantic mapping dataset featuring realistic city layouts, high-fidelity rendering, and instance-level annotations spanning multiple object scales. We then propose a category-aware likelihood calibration policy that identifies and alleviates unreliable observations according to object category and viewing distance. Because the calibration and motion policies are optimized toward the same mapping objective, they may learn redundant shortcuts and become excessively coupled. We therefore introduce a mutual-information (MI) regularizer that penalizes their estimated representation dependence and encourages complementary behaviors. To better model heterogeneous mapping strategies across object scales, we further employ category-wise value estimators. We formulate their joint optimization as a Pareto optimization problem to mitigate conflicting gradients across categories.
NaviScale is proposed for semantic-map-based object navigation (ObjectNav), whose predictor can be trained on pairs of partial and complete semantic maps without reconstructing a complete 3D environment for every training sample.
Robots operating in dynamic environments require reliable detection of how their surroundings change over time. Existing learning-based methods largely rely on pairwise 2D image features, which struggle under large viewpoint changes and occlusions, are sensitive to noise, and show limited generalization across domains,...
Rui-Han Xu, Jia Yoon, Kai-Chen Zhou et al.· 0 citations
Predictive mapping can support robotic exploration and navigation by estimating unseen geometric layouts from partial occupancy observations. However, occupancy-only representations may fail to distinguish semantically different structures with similar geometry. This is particularly relevant for indoor doors, which may...
Remote sensing imagery is characterized by complex backgrounds, substantial scale variation, and numerous small targets, placing greater demands on semantic modeling of high-spatial-resolution features and feature integration across multiple scales. Within the D-FINE hybrid encoder, however, the relatively high-spatial...
Gao-Shan Song, Kan Chen, Guo-Qiang Chu et al.· Electronics· 0 citations
Remote Sensing Image Change Captioning (RSICC) aims to describe the differences between two images with a short description. Existing methods conventionally concentrate on optical imagery under clear-sky conditions, failing to account for complex multimodal environmental influences (e.g., clouds, haze, low-light condit...
Jia Liu, Qian Li, Kai-Yi Zhang et al.· 0 citations
Scene Coordinate Regression (SCR) has recently emerged as a promising approach for LiDAR-based localization, achieving accurate localization without requiring an explicit 3D map. Despite their effectiveness, existing SCR methods rely on scene classification-based global embedding that struggles to provide fine-grained...
Heejoon Moon, Yurim Cho, J. Hong· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.