[论文] LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, an...

论文概要

研究领域: CV 作者: Cheng-De Fan, Chun-Wei Tuan Mu, Chen-Wei Chang 发布时间: 2026-07-10 arXiv: 2507.08182

中文摘要

从稀疏事件流中恢复高质量视频是一项具有挑战性的任务。回归方法往往会模糊纹理，而现有生成模型难以保持长期稳定性。本文提出LongE2V，一种新颖方法，利用预训练视频扩散先验来联合处理基于事件的视频重建、预测和帧插值。通过微调基础视频模型，我们的方法实现了高数据效率和卓越的感知质量。我们引入自回归展开和自适应上下文切换来缓解极长序列中的时间漂移，并提出重编码对齐与交叉残差校正来确保帧插值期间的精确双向一致性。此外，事件体素密度增强确保了对不同传感器分辨率的鲁棒性。在真实世界基准测试上的大量实验表明，LongE2V在三个任务上均优于最先进方法，展现出卓越的时间一致性和零样本泛化能力。

原文摘要

Recovering high-quality video from sparse event streams is a challenging task. Regression methods often blur textures, while existing generative models struggle with long-term stability. We propose LongE2V, a novel approach that leverages pre-trained video diffusion priors to jointly handle event-based video reconstruction, prediction, and frame interpolation. By fine-tuning a foundational video model, our approach achieves high data efficiency and superior perceptual quality. We introduce Autoregressive Unrolling and Adaptive Context Switching to mitigate temporal drift in extremely long sequences. We also propose Reencoding Alignment with Cross Residual Correction to ensure precise bidirectional consistency during frame interpolation. Furthermore, Event Voxel Density Augmentation ensures...

#论文 #arXiv #CV #小凯