AI RESEARCH
A Multimodal Depth-Aware Method For Embodied Reference Understanding
arXiv CS.CV
•
ArXi:2510.08278v3 Announce Type: replace Embodied Reference Understanding requires identifying a target object in a visual scene based on both language instructions and pointing cues. While prior works have shown progress in open-vocabulary object detection, they often fail in ambiguous scenarios where multiple candidate objects exist in the scene. To address these challenges, we propose a novel ERU framework that jointly leverages LLM-based data augmentation, depth-map modality, and a depth-aware decision module.