LidaRefer: Context-aware Outdoor 3D Visual Grounding for Autonomous Driving
This work solves the specific problem of accurately locating objects in large-scale outdoor LiDAR scenes for autonomous driving applications, representing a domain-specific advancement.
The paper tackles the problem of 3D visual grounding in outdoor autonomous driving scenes by addressing challenges like background dominance and lack of referential object annotations, resulting in state-of-the-art performance on the Talk2Car-3D dataset.
3D visual grounding (VG) aims to locate objects or regions within 3D scenes guided by natural language descriptions. While indoor 3D VG has advanced, outdoor 3D VG remains underexplored due to two challenges: (1) large-scale outdoor LiDAR scenes are dominated by background points and contain limited foreground information, making cross-modal alignment and contextual understanding more difficult; and (2) most outdoor datasets lack spatial annotations for referential non-target objects, which hinders explicit learning of referential context. To this end, we propose LidaRefer, a context-aware 3D VG framework for outdoor scenes. LidaRefer incorporates an object-centric feature selection strategy to focus on semantically relevant visual features while reducing computational overhead. Then, its transformer-based encoder-decoder architecture excels at establishing fine-grained cross-modal alignment between refined visual features and word-level text features, and capturing comprehensive global context. Additionally, we present Discriminative-Supportive Collaborative localization (DiSCo), a novel supervision strategy that explicitly models spatial relationships between target, contextual, and ambiguous objects for accurate target identification. To enable this without manual labeling, we introduce a pseudo-labeling approach that retrieves 3D localization labels for referential non-target objects. LidaRefer achieves state-of-the-art performance on Talk2Car-3D dataset under various evaluation settings.