{"ID":2833183,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.05240","arxiv_id":"2512.05240","title":"IE2Video: Adapting Pretrained Diffusion Models for Event-Based Video Reconstruction","abstract":"Continuous video monitoring in surveillance, robotics, and wearable systems faces a fundamental power constraint: conventional RGB cameras consume substantial energy through fixed-rate capture. Event cameras offer sparse, motion-driven sensing with low power consumption, but produce asynchronous event streams rather than RGB video. We propose a hybrid capture paradigm that records sparse RGB keyframes alongside continuous event streams, then reconstructs full RGB video offline -- reducing capture power consumption while maintaining standard video output for downstream applications. We introduce the Image and Event to Video (IE2Video) task: reconstructing RGB video sequences from a single initial frame and subsequent event camera data. We investigate two architectural strategies: adapting an autoregressive model (HyperE2VID) for RGB generation, and injecting event representations into a pretrained text-to-video diffusion model (LTX) via learned encoders and low-rank adaptation. Our experiments demonstrate that the diffusion-based approach achieves 33\\% better perceptual quality than the autoregressive baseline (0.283 vs 0.422 LPIPS). We validate our approach across three event camera datasets (BS-ERGB, HS-ERGB far/close) at varying sequence lengths (32-128 frames), demonstrating robust cross-dataset generalization with strong performance on unseen capture configurations.","short_abstract":"Continuous video monitoring in surveillance, robotics, and wearable systems faces a fundamental power constraint: conventional RGB cameras consume substantial energy through fixed-rate capture. Event cameras offer sparse, motion-driven sensing with low power consumption, but produce asynchronous event streams rather th...","url_abs":"https://arxiv.org/abs/2512.05240","url_pdf":"https://arxiv.org/pdf/2512.05240v1","authors":"[\"Dmitrii Torbunov\",\"Onur Okuducu\",\"Yi Huang\",\"Odera Dim\",\"Rebecca Coles\",\"Yonggang Cui\",\"Yihui Ren\"]","published":"2025-12-04T20:37:45Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}