{"ID":3083739,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T07:23:37.79250861Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.06142","arxiv_id":"2606.06142","title":"Computation-Aware Event-to-Frame Reconstruction via Selective Attention","abstract":"Event-to-frame (E2F) reconstruction bridges asynchronous event streams with frame-based vision pipelines, but existing methods often face a trade-off between reconstruction quality and computational efficiency. In this work, we propose an efficient E2F framework that emphasizes causal temporal modeling and computation-aware design. The architecture adopts a recurrent encoder-decoder to incrementally aggregate event information with compact hidden states. To improve robustness under fast motion and illumination variations, a selective context fusion strategy is introduced to integrate event-driven features with prior intensity cues. Within this fusion process, a lightweight hybrid attention mechanism enhances feature selectivity without relying on heavy attention operations. Experimental results on standard benchmarks demonstrate that the proposed approach achieves competitive reconstruction performance while maintaining a favorable balance between accuracy and model complexity.","short_abstract":"Event-to-frame (E2F) reconstruction bridges asynchronous event streams with frame-based vision pipelines, but existing methods often face a trade-off between reconstruction quality and computational efficiency. In this work, we propose an efficient E2F framework that emphasizes causal temporal modeling and computation-...","url_abs":"https://arxiv.org/abs/2606.06142","url_pdf":"https://arxiv.org/pdf/2606.06142v1","authors":"[\"Jingqian Wu\",\"Yunbo Jia\",\"Edmund Y. Lam\"]","published":"2026-06-04T13:19:59Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}