Do MLLMs Understand Pointing? Benchmarking and Enhancing Referential Reasoning in Egocentric Vision
For developers of egocentric AI agents (e.g., smart glasses), this work addresses the critical problem of grounding pointing gestures in language commands, which is currently poorly handled by MLLMs.
The paper introduces EgoPoint-Bench, a benchmark with over 11k samples to evaluate multimodal pointing reasoning in egocentric views, revealing that current MLLMs suffer from 'Referential Hallucination' and that fine-tuning on synthetic data yields significant performance gains with robust sim-to-real generalization.
Egocentric AI agents, such as smart glasses, rely on pointing gestures to resolve referential ambiguities in natural language commands. However, despite advancements in Multimodal Large Language Models (MLLMs), current systems often fail to precisely ground the spatial semantics of pointing. Instead, they rely on spurious correlations with visual proximity or object saliency, a phenomenon we term "Referential Hallucination." To address this gap, we introduce EgoPoint-Bench, a comprehensive question-answering benchmark designed to evaluate and enhance multimodal pointing reasoning in egocentric views. Comprising over 11k high-fidelity simulated and real-world samples, the benchmark spans five evaluation dimensions and three levels of referential complexity. Extensive experiments demonstrate that while state-of-the-art proprietary and open-source models struggle with egocentric pointing, models fine-tuned on our synthetic data achieve significant performance gains and robust sim-to-real generalization. This work highlights the importance of spatially aware supervision and offers a scalable path toward precise egocentric AI assistants. Project page: https://guyyyug.github.io/EgoPoint-Bench/