{"ID":2831359,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.09016","arxiv_id":"2512.09016","title":"Learning to Remove Lens Flare in Event Camera","abstract":"Event cameras have the potential to revolutionize vision systems with their high temporal resolution and dynamic range, yet they remain susceptible to lens flare, a fundamental optical artifact that causes severe degradation. In event streams, this optical artifact forms a complex, spatio-temporal distortion that has been largely overlooked. We present E-Deflare, the first systematic framework for removing lens flare from event camera data. We first establish the theoretical foundation by deriving a physics-grounded forward model of the non-linear suppression mechanism. This insight enables the creation of the E-Deflare Benchmark, a comprehensive resource featuring a large-scale simulated training set, E-Flare-2.7K, and the first-ever paired real-world test set, E-Flare-R, captured by our novel optical system. Empowered by this benchmark, we design E-DeflareNet, which achieves state-of-the-art restoration performance. Extensive experiments validate our approach and demonstrate clear benefits for downstream tasks. Code and datasets are publicly available.","short_abstract":"Event cameras have the potential to revolutionize vision systems with their high temporal resolution and dynamic range, yet they remain susceptible to lens flare, a fundamental optical artifact that causes severe degradation. In event streams, this optical artifact forms a complex, spatio-temporal distortion that has b...","url_abs":"https://arxiv.org/abs/2512.09016","url_pdf":"https://arxiv.org/pdf/2512.09016v1","authors":"[\"Haiqian Han\",\"Lingdong Kong\",\"Jianing Li\",\"Ao Liang\",\"Chengtao Zhu\",\"Jiacheng Lyu\",\"Lai Xing Ng\",\"Xiangyang Ji\",\"Wei Tsang Ooi\",\"Benoit R. Cottereau\"]","published":"2025-12-09T18:59:57Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}