Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation

Researchers introduced Ego Scene Augmentation (ESA), a framework that enhances spatial perception in multimodal large language models for egocentric visual question answering, achieving over 8% accuracy gains on the EgoTextVQA benchmark in both indoor and outdoor settings.

arXiv:2607.14497v1 Announce Type: new Abstract: Egocentric Visual Question Answering VQA has attracted widespread attention as an important task for enabling Multimodal Large Language Models MLLMs to interact with the real world. However, existing MLLMs struggle to perform effective spatial reasoning in complex egocentric scenes due to their limited spatial perception capabilities. To this end, we introduce Ego Scene Augmentation ESA , an egocentric spatial perception framework, which actively enhances the spatial perception capabilities from the egocentric perspective, powered by the proposed Ego-element Graph. Our core insight is leveraging the Ego-element Graph as an intermediary representation to augment the egocentric spatial perception of MLLMs via visual foundational models. Specifically, we 1 construct the Ego-element Graph, which encapsulates and integrates egocentric spatial features enabled by visual foundational models; 2 enhance the spatial perception capabilities of MLLMs via the Ego-element Graph for ego-perspective scenes. Our proposed ESA framework presents significant performance improvement on the EgoTextVQA benchmark. We achieve an 8.14% gain on the indoor setting and an 8.72% gain on the outdoor setting. Furthermore, our ESA shows the most impressive performance improvement in the shopping subset of the indoor setting. The project code is publicly available.