SATMapTR: Satellite Image Enhanced Online HD Map Construction

2025-12-12

AI Summary

To address incomplete, noisy, and brittle high-definition (HD) map construction caused by limited field-of-view and frequent occlusions of onboard sensors, this paper proposes a satellite-image-augmented online real-time mapping method. Our approach introduces three key innovations: (1) a gated feature refinement module for semantic-structural adaptive filtering; (2) a geometry-aware fusion module enabling voxel-level cross-view geometric alignment; and (3) a geometrically constrained attention mechanism integrating Transformer-based bird’s-eye-view (BEV) encoding, multi-scale satellite feature extraction, and explicit geometric priors. Evaluated on nuScenes, our method achieves 73.8 mAP—surpassing the state-of-the-art by 14.2 percentage points. It demonstrates significantly improved robustness under adverse weather conditions and sensor failures, and boosts long-range perception mAP by nearly 3×.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Feature Construction/Reformulation

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

High-definition (HD) maps are evolving from pre-annotated to real-time construction to better support autonomous driving in diverse scenarios. However, this process is hindered by low-quality input data caused by onboard sensors limited capability and frequent occlusions, leading to incomplete, noisy, or missing data, and thus reduced mapping accuracy and robustness. Recent efforts have introduced satellite images as auxiliary input, offering a stable, wide-area view to complement the limited ego perspective. However, satellite images in Bird's Eye View are often degraded by shadows and occlusions from vegetation and buildings. Prior methods using basic feature extraction and fusion remain ineffective. To address these challenges, we propose SATMapTR, a novel online map construction model that effectively fuses satellite image through two key components: (1) a gated feature refinement module that adaptively filters satellite image features by integrating high-level semantics with low-level structural cues to extract high signal-to-noise ratio map-relevant representations; and (2) a geometry-aware fusion module that consistently fuse satellite and BEV features at a grid-to-grid level, minimizing interference from irrelevant regions and low-quality inputs. Experimental results on the nuScenes dataset show that SATMapTR achieves the highest mean average precision (mAP) of 73.8, outperforming state-of-the-art satellite-enhanced models by up to 14.2 mAP. It also shows lower mAP degradation under adverse weather and sensor failures, and achieves nearly 3 times higher mAP at extended perception ranges.

Problem

• Enhances online HD map construction using satellite images
• Addresses low-quality input from onboard sensors and occlusions
• Improves mapping accuracy and robustness in diverse scenarios

Innovation

• Gated feature refinement module filters satellite images adaptively
• Geometry-aware fusion module integrates satellite and BEV features grid-to-grid
• SATMapTR achieves highest mAP on nuScenes dataset outperforming prior models