mlsanityData to 14 Oct 2026

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

arXiv 2505.19858 ↗First posted 26 May 2025cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 45 of its 87 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

45 of 87 references.

References · 45

  1. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  2. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 957
  3. 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 342
  4. 2022Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detectioncited by 317
  5. 2022CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusioncited by 223
  6. 2022VRT: A Video Restoration Transformercited by 220
  7. 2018DenseFuse: A Fusion Approach to Infrared and Visible Imagescited by 180
  8. 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 174
  9. 2023DDFM: Denoising Diffusion Model for Multi-Modality Image Fusioncited by 153
  10. 2023Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentationcited by 129
  11. 2023Equivariant Multi-Modality Image Fusioncited by 99
  12. 2023LRRNet: A Novel Representation Learning Guided Fusion Network for Infrared and Visible Imagescited by 87
33 more
  1. 2022Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registrationcited by 80
  2. 2019Deep Convolutional Neural Network for Multi-modal Image Restoration and Fusioncited by 79
  3. 2017DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairscited by 78
  4. 2020DIDFuse: Deep Image Decomposition for Infrared and Visible Image Fusioncited by 73
  5. 2021Discrete Cosine Transform Network for Guided Depth Map Super-Resolutioncited by 71
  6. 2024Task-Customized Mixture of Adapters for General Image Fusioncited by 59
  7. 2021HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Datasetcited by 45
  8. 2021Deep Gradient Projection Networks for Pan-sharpeningcited by 44
  9. 2024Image Fusion via Vision-Language Modelcited by 40
  10. 2013Medical Image Fusion: A survey of the state of the artcited by 39
  11. 2024USTC-TD: A Test Dataset and Benchmark for Image and Video Coding in 2020scited by 37
  12. 2025DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusioncited by 34
  13. 2021TransMEF: A Transformer-Based Multi-Exposure Image Fusion Framework using Self-Supervised Multi-Task Learningcited by 32
  14. 2025One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusioncited by 32
  15. 2024HDRFlow: Real-Time HDR Video Reconstruction with Large Motionscited by 31
  16. 2024Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Modelcited by 31
  17. 2024Video Depth without Video Modelscited by 29
  18. 2024Task-driven Image Fusion with Learnable Fusion Losscited by 25
  19. 2025UltraFusion: Ultra High Dynamic Imaging using Exposure Fusioncited by 21
  20. 2023LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstructioncited by 18
  21. 2025PolarFree: Polarization-based Reflection-free Imagingcited by 18
  22. 2023ReFusion: Learning Image Fusion from Reconstruction with Learnable Loss via Meta-Learningcited by 15
  23. 2023Mutual-Guided Dynamic Network for Image Fusioncited by 14
  24. 2024Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Networkcited by 14
  25. 2024DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolutioncited by 14
  26. 2020MFFW: A new dataset for multi-focus image fusioncited by 13
  27. 2024Visible-Thermal Multiple Object Tracking: Large-scale Video Dataset and Progressive Fusion Approachcited by 13
  28. 2023Searching a Compact Architecture for Robust Multi-Exposure Image Fusioncited by 11
  29. 2024YouTube SFV+HDR Quality Datasetcited by 9
  30. 2025VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusioncited by 8
  31. 2019An α-Matte Boundary Defocus Model Based Cascaded Network for Multi-focus Image Fusioncited by 7
  32. 2025Deep Unfolding Multi-modal Image Fusion Network via Attribution Analysiscited by 7
  33. 2024BSAFusion: A Bidirectional Stepwise Feature Alignment Network for Unaligned Medical Image Fusioncited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 6.

9 papers.

  1. 2025ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichmentcited by 27
  2. 2025OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimizationcited by 14
  3. 2025MultiMotion: Multi Subject Video Motion Transfer via Video Diffusion Transformercited by 3
  4. 2026MambaVF: State Space Model for Efficient Video Fusioncited by 1
  5. 2026Adding Thermal Awareness to Visual Systems in Real-Time via Distilled Diffusion Modelscited by 1
  6. 2026Robust Self-Supervised Cross-Modal Super-Resolution against Real-World Misaligned Observationscited by 0
  7. 2026FTPFusion: Frequency-Aware Infrared and Visible Video Fusion with Temporal Perturbationcited by 0
  8. 2026MAVFusion: Efficient Infrared and Visible Video Fusion via Motion-Aware Sparse Interactioncited by 0
  9. 2026DRFusion: Drift-Resilient Temporally Consistent Infrared-Visible Video Fusioncited by 0