Search papers, labs, and topics across Lattice.
The paper introduces EventFace, a novel framework for event-based face recognition that leverages structure-driven spatiotemporal modeling to overcome the challenges posed by the lack of photometric appearance in event streams. They transfer structural facial priors from pretrained RGB face models to the event domain using LoRA and introduce a Motion Prompt Encoder (MPE) and Spatiotemporal Modulator (STM) to encode and fuse temporal features with spatial features. Experiments on a newly constructed event-based face dataset (EFace) demonstrate that EventFace achieves state-of-the-art performance with a Rank-1 identification rate of 94.19% and improved robustness under degraded illumination.
Event cameras can now achieve surprisingly high face recognition accuracy, even under poor lighting, by transferring knowledge from standard RGB face models.
Event cameras offer a promising sensing modality for face recognition due to their inherent advantages in illumination robustness and privacy-friendliness. However, because event streams lack the stable photometric appearance relied upon by conventional RGB-based face recognition systems, we argue that event-based face recognition should model structure-driven spatiotemporal identity representations shaped by rigid facial motion and individual facial geometry. Since dedicated datasets for event-based face recognition remain lacking, we construct EFace, a small-scale event-based face dataset captured under rigid facial motion. To learn effectively from this limited event data, we further propose EventFace, a framework for event-based face recognition that integrates spatial structure and temporal dynamics for identity modeling. Specifically, we employ Low-Rank Adaptation (LoRA) to transfer structural facial priors from pretrained RGB face models to the event domain, thereby establishing a reliable spatial basis for identity modeling. Building on this foundation, we further introduce a Motion Prompt Encoder (MPE) to explicitly encode temporal features and a Spatiotemporal Modulator (STM) to fuse them with spatial features, thereby enhancing the representation of identity-relevant event patterns. Extensive experiments demonstrate that EventFace achieves the best performance among the evaluated baselines, with a Rank-1 identification rate of 94.19% and an equal error rate (EER) of 5.35%. Results further indicate that EventFace exhibits stronger robustness under degraded illumination than the competing methods. In addition, the learned representations exhibit reduced template reconstructability.
