SCAFusion: A Multimodal 3D Detection Framework for Small Object Detection in Lunar Surface Exploration

TL;DR

SCAFusion is a multimodal 3D detection framework specifically designed for small object detection in lunar surface exploration, improving accuracy through novel modules while maintaining efficiency.

Contribution

The paper introduces SCAFusion, a tailored multimodal 3D detection model with new modules for better small object detection in lunar environments, built on the BEVFusion framework.

Findings

Achieves 69.7% mAP on nuScenes, surpassing baseline by 5.0%.

Attains 90.93% mAP in lunar simulation, outperforming baseline by 11.5%.

Enhances small object detection accuracy with minimal computational overhead.

Abstract

Reliable and precise detection of small and irregular objects, such as meteor fragments and rocks, is critical for autonomous navigation and operation in lunar surface exploration. Existing multimodal 3D perception methods designed for terrestrial autonomous driving often underperform in off world environments due to poor feature alignment, limited multimodal synergy, and weak small object detection. This paper presents SCAFusion, a multimodal 3D object detection model tailored for lunar robotic missions. Built upon the BEVFusion framework, SCAFusion integrates a Cognitive Adapter for efficient camera backbone tuning, a Contrastive Alignment Module to enhance camera LiDAR feature consistency, a Camera Auxiliary Training Branch to strengthen visual representation, and most importantly, a Section aware Coordinate Attention mechanism explicitly designed to boost the detection performance of small, irregular targets. With negligible increase in parameters and computation, our model achieves 69.7% mAP and 72.1% NDS on the nuScenes validation set, improving the baseline by 5.0% and 2.7%, respectively. In simulated lunar environments built on Isaac Sim, SCAFusion achieves 90.93% mAP, outperforming the baseline by 11.5%, with notable gains in detecting small meteor like obstacles.