paper-with-me

Papers

A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking

2025-05-26 · Zixiang Zhao, Haowen Bai, Bingxin Ke, Yukun Cui, Lilun Deng, Yulun Zhang, Kai Zhang, Konrad Schindler

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: https://vfbench.github.io.

📄 PDF Abstract BibTeX arXiv:2505.19858

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingOptical Flow EstimationSynthetic Data Generation

Similar Papers 제목 키워드 기반

Bridging Video Understanding and Generation in a Unified Framework

2026-06-30 · Yuqi Wang, Runyi Li, Ruoyu Feng, Renjie Chen 외 arxiv

Recently, unified image generation and understanding have been extensively explored. However, extending such unified modeling paradigms to the video domain remains largely underexplored. A central challenge is that video…

Video GenerationImage Generation

UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution

2025-10-09 · Shian Du, Menghan Xia, Chang Liu, Quande Liu 외 arxiv

Cascaded video super-resolution has emerged as a promising technique for decoupling the computational burden associated with generating high-resolution videos using large foundation models. Existing studies, however, are…

Video Super-ResolutionVideo Generation

Reangle-A-Video: 4D Video Generation as Video-to-Video Translation

2025-03-12 · Hyeonho Jeong, Suhyeon Lee, Jong Chul Ye

We introduce Reangle-A-Video, a unified framework for generating synchronized multi-view videos from a single input video. Unlike mainstream approaches that train multi-view video diffusion models on large-scale 4D datas…

TranslationVideo Generation

TDM: Temporally-Consistent Diffusion Model for All-in-One Real-World Video Restoration

2025-01-04 · Yizhou Li, Zihua Liu, Yusuke Monno, Masatoshi Okutomi

In this paper, we propose the first diffusion-based all-in-one video restoration method that utilizes the power of a pre-trained Stable Diffusion and a fine-tuned ControlNet. Our method can restore various types of video…

AllDenoisingVideo Restoration

IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation

2025-06-03 · Yuanze Lin, Yi-Wen Chen, Yi-Hsuan Tsai, Ronald Clark 외

Although diffusion-based models can generate high-quality and high-resolution video sequences from textual or image inputs, they lack explicit integration of geometric cues when controlling scene lighting and visual appe…

3D geometryVideo Generation