Bridging the Gap Between Sparsity and Redundancy: A Dual-Decoding Framework with Global Context for Map Inference

2025-09-15

AI Summary

Trajectory data exhibit spatially non-uniform density, leading to road fragmentation in sparse regions and spurious connections in dense regions during map inference. To address this, we propose a global context-aware dual-decoder framework. First, a multi-scale grid encoding scheme coupled with masked augmentation enhances keypoint detection accuracy—particularly in sparse areas. Second, a global relational prediction module is introduced to explicitly model long-range trajectory dependencies, thereby suppressing erroneous edge connections. Crucially, our framework is the first to achieve dynamic fusion of local geometric features and global semantic information within a dual-decoder architecture. Extensive experiments on three real-world trajectory datasets demonstrate that our method achieves a 5% improvement in APLS over state-of-the-art approaches; gains are especially pronounced on DiDi’s large-scale trajectory dataset.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Trajectory data has become a key resource for automated map in-ference due to its low cost, broad coverage, and continuous availability. However, uneven trajectory density often leads to frag-mented roads in sparse areas and redundant segments in dense regions, posing significant challenges for existing methods. To address these issues, we propose DGMap, a dual-decoding framework with global context awareness, featuring Multi-scale Grid Encoding, Mask-enhanced Keypoint Extraction, and Global Context-aware Relation Prediction. By integrating global semantic context with local geometric features, DGMap improves keypoint detection accuracy to reduce road fragmentation in sparse-trajectory areas. Additionally, the Global Context-aware Relation Prediction module suppresses false connections in dense-trajectory regions by modeling long-range trajectory patterns. Experimental results on three real-world datasets show that DGMap outperforms state-of-the-art methods by 5% in APLS, with notable performance gains on trajectory data from the Didi Chuxing platform

Problem

• Addressing fragmented roads in sparse trajectory areas
• Reducing redundant segments in dense trajectory regions
• Improving map inference accuracy with global context

Innovation

• Dual-decoding framework with global context
• Multi-scale Grid Encoding for feature integration
• Global Context-aware Relation Prediction module