ESAFusion: LiDAR--4-D Radar Fusion via Local Geometric Complementation and Multiscale Adaptive Interaction for 3-D Object Detection

2026-09-13

AI Summary

ESAFusion通过局部几何互补和多尺度自适应交互解决LiDAR-4D雷达融合中的稀疏观测与空间采样不匹配问题，提高复杂驾驶环境下的3D目标检测精度。

Abstract

LiDAR--4-D radar fusion combines accurate spatial geometry with motion and reflectivity cues from radar, offering a promising solution for 3-D object detection in complex driving environments. However, sparse radar observations and differences in spatial sampling between the two modalities complicate reliable cross-modal complementation. Moreover, the relative importance of modalities and feature scales varies across spatial regions, making adaptive fusion challenging. To address these challenges, we propose ESAFusion, an evidence-aware and scale-adaptive framework that combines local geometric complementation with multiscale adaptive interaction. Specifically, we introduce an Evidence-Aware Radar Selection (ERS) module to suppress radar clutter using motion and observation-quality evidence while retaining foreground confidence for subsequent fusion. Then, the Pillar-Level Complementary Encoder (PCE) improves cross-modal complementation under mismatched spatial sampling using local geometric support from neighboring LiDAR pillars. We further design an Intra- and Inter-Scale Adaptive Fusion (ISAF) module to adaptively adjust the contributions of different modalities and feature scales in bird's-eye-view (BEV) space. Extensive experiments on the View-of-Delft (VoD) dataset show that ESAFusion achieves the highest mean average precision (mAP) among the compared methods, reaching 74.60% in the Entire Annotated Area and 88.89% in the Driving Corridor. It also attains the highest average precision (AP) for Cyclist among these methods in both regions while running at 19.23 FPS. Evaluations on VoD-Fog further demonstrate robustness under progressively degraded LiDAR observations. The source code will be made publicly available at https://github.com/SenJieHu549/ESAFusion.

Problem

• LiDAR-4D Radar Fusion
• Sparse Radar Observations
• Spatial Sampling Differences
• Adaptive Fusion
• 3D Object Detection

Innovation

• Evidence-Aware Radar Selection
• Pillar-Level Complementary Encoder
• Intra- and Inter-Scale Adaptive Fusion