Skip to content

Multi-Scale Semantic Mapping in Urban Environments via Observation Calibration and Policy Dependence Regularization

Sep 2026 · arXiv.org · Vol abs/2609.34833 · 0 citations · 49 references
Computer Science

TL;DR

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.

View source

Similar papers

Sep 2026

NaviScale: Generating Large-Scale Semantic Map Datasets for Object Navigation

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.

Chuan-Lin Lan, Yan-Wei Zheng, Yu-Xin Jing et al. · 0 citations
Preprint Oct 2026

Argos: Adapt Rich Geometric Priors for Generalizable Online Scene-Change-Detection

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
Preprint Oct 2026

Semantic-Aware Predictive Mapping for Exploration and Navigation

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...

Kenneth J. K. Ong, William W. J. Teo · 0 citations
Open access Oct 2026

OSPIR-DETR: Object-Selective Proxy Interaction and Gain-Guided Scale Alignment for Remote Sensing Object Detection

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. · 0 citations
Book Open access Nov 2026

Environment-Aware Trajectory and Object-Location-Guided Refinement for Fine-grained Remote Sensing Change Captioning

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
Sep 2026

ReLoc: Rethinking Scene Coordinate Regression Architecture for Robust Outdoor LiDAR-based Localization

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 · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.