A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909859574710272 |
|---|---|
| author | Zhao, Zixiang Bai, Haowen Ke, Bingxin Cui, Yukun Deng, Lilun Zhang, Yulun Zhang, Kai Schindler, Konrad |
| author_facet | Zhao, Zixiang Bai, Haowen Ke, Bingxin Cui, Yukun Deng, Lilun Zhang, Yulun Zhang, Kai Schindler, Konrad |
| contents | 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 and unified framework for 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: https://vfbench.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19858 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking Zhao, Zixiang Bai, Haowen Ke, Bingxin Cui, Yukun Deng, Lilun Zhang, Yulun Zhang, Kai Schindler, Konrad Computer Vision and Pattern Recognition 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 and unified framework for 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: https://vfbench.github.io. |
| title | A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.19858 |