Abstract
The real world is dynamic, yet most image fusion methods process static frames independently, ignoring temporal correlations in videos and leading to flickering and temporal inconsistency. To address this, we propose Unified Video Fusion (UniVF), a novel framework for temporally coherent video fusion that leverages multi-frame learning and optical flow-based feature warping for informative, temporally coherent video fusion. To support its development, we also introduce Video Fusion Benchmark (VF-Bench), the first comprehensive benchmark covering four video fusion tasks: multi-exposure, multi-focus, infrared-visible, and medical fusion. VF-Bench provides high-quality, well-aligned video pairs obtained through synthetic data generation and rigorous curation from existing datasets, with a unified evaluation protocol that jointly assesses the spatial quality and temporal consistency of video fusion. Extensive experiments show that UniVF achieves state-of-the-art results across all tasks on VF-Bench. Project page: this https URL.
Abstract (translated)
现实世界是动态的，但大多数图像融合方法处理的是静态帧，并且忽略了视频中的时间相关性，导致闪烁和时间上的一致性问题。为了解决这个问题，我们提出了统一视频融合（Unified Video Fusion, UniVF），这是一种新颖的框架，用于生成具有时间一致性的视频融合结果，它利用多帧学习和基于光学流的特征扭曲技术来实现信息丰富且时间上连贯的视频融合。为了支持其开发，我们也引入了视频融合基准测试（Video Fusion Benchmark, VF-Bench），这是第一个全面的基准测试集，涵盖了四种视频融合任务：多曝光、多焦点、红外-可见光和医学图像融合。VF-Bench提供了高质量、精确对齐的视频配对，这些数据通过合成数据生成并从现有数据集中严格筛选出来，并提供了一个统一的评估协议，用于共同评估视频融合的空间质量和时间一致性。广泛的实验表明，在VF-Bench的所有任务上，UniVF都达到了最先进的结果。 项目页面：[此链接](https://this-url.com)。
URL
https://arxiv.org/abs/2505.19858
