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.
View on arXiv@article{zhao2025_2505.19858,
title={ A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking },
author={ Zixiang Zhao and Haowen Bai and Bingxin Ke and Yukun Cui and Lilun Deng and Yulun Zhang and Kai Zhang and Konrad Schindler },
journal={arXiv preprint arXiv:2505.19858},
year={ 2025 }
}