VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion and Restoration

• URL: http://arxiv.org/abs/2503.23359v2
• Date: Fri, 27 Jun 2025 11:59:17 GMT
• Title: VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion and Restoration
• Authors: Linfeng Tang, Yeda Wang, Meiqi Gong, Zizhuo Li, Yuxin Deng, Xunpeng Yi, Chunyu Li, Han Xu, Hao Zhang, Jiayi Ma,
• Abstract summary: Existing multi-sensor fusion research predominantly integrates complementary from multiple images rather than videos.<n>VideoFusion exploits cross-modal complementarity and temporal dynamics to generate context-temporally coherent videos.<n>Extensive experiments reveal that VideoFusion outperforms existing image-oriented fusion paradigms in sequential scenarios.
• Score: 26.59510171451438
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Compared to images, videos better align with real-world acquisition scenarios and possess valuable temporal cues. However, existing multi-sensor fusion research predominantly integrates complementary context from multiple images rather than videos. This primarily stems from two factors: 1) the scarcity of large-scale multi-sensor video datasets, limiting research in video fusion, and 2) the inherent difficulty of jointly modeling spatial and temporal dependencies in a unified framework. This paper proactively compensates for the dilemmas. First, we construct M3SVD, a benchmark dataset with $220$ temporally synchronized and spatially registered infrared-visible video pairs comprising 153,797 frames, filling the data gap for the video fusion community. Secondly, we propose VideoFusion, a multi-modal video fusion model that fully exploits cross-modal complementarity and temporal dynamics to generate spatio-temporally coherent videos from (potentially degraded) multi-modal inputs. Specifically, 1) a differential reinforcement module is developed for cross-modal information interaction and enhancement, 2) a complete modality-guided fusion strategy is employed to adaptively integrate multi-modal features, and 3) a bi-temporal co-attention mechanism is devised to dynamically aggregate forward-backward temporal contexts to reinforce cross-frame feature representations. Extensive experiments reveal that VideoFusion outperforms existing image-oriented fusion paradigms in sequential scenarios, effectively mitigating temporal inconsistency and interference.

Related papers

• DCDM: Divide-and-Conquer Diffusion Models for Consistency-Preserving Video Generation [77.89090846233906]
  We propose a system-level framework, termed the Divide-and-Conquer Diffusion Model (DCDM)<n>DCDM decomposes video consistency modeling into three dedicated components while sharing a unified video generation backbone.<n>We validate our framework on the test set of the CVM Competition at AAAI'26, and the results demonstrate that the proposed strategies effectively address these challenges.
  arXiv  Detail & Related papers  (2026-02-14T07:02:36Z)
• LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation [35.01134463094784]
  Real-time video generation via diffusion is essential for building general-purpose multimodal interactive AI systems.<n>Existing distillation methods can make the model autoregressive and reduce sampling steps to mitigate this.<n>This paper targets real-time interactive video diffusion conditioned on a multimodal context, including text, image, and audio, to bridge the gap.
  arXiv  Detail & Related papers  (2025-12-29T16:17:36Z)
• BindWeave: Subject-Consistent Video Generation via Cross-Modal Integration [56.98981194478512]
  We propose a unified framework that handles a broad range of subject-to-video scenarios.<n>We introduce an MLLM-DiT framework in which a pretrained multimodal large language model performs deep cross-modal reasoning to ground entities.<n>Experiments on the OpenS2V benchmark demonstrate that our method achieves superior performance across subject consistency, naturalness, and text relevance in generated videos.
  arXiv  Detail & Related papers  (2025-10-01T02:41:11Z)
• Query-Kontext: An Unified Multimodal Model for Image Generation and Editing [53.765351127477224]
  Unified Multimodal Models (UMMs) have demonstrated remarkable performance in text-to-image generation (T2I) and editing (TI2I)<n>We introduce Query-Kontext, a novel approach that bridges the VLM and diffusion model via a multimodal kontext'' composed of semantic cues and coarse-grained image conditions encoded from multimodal inputs.<n> Experiments show that our approach matches strong unified baselines and even outperforms task-specific state-of-the-art methods in several cases.
  arXiv  Detail & Related papers  (2025-09-30T17:59:46Z)
• TemCoCo: Temporally Consistent Multi-modal Video Fusion with Visual-Semantic Collaboration [36.255570023185506]
  Existing multi-modal fusion methods apply static frame-based image fusion techniques directly to video fusion tasks.<n>We propose the first video fusion framework that explicitly incorporates temporal modeling with visual-semantic collaboration.
  arXiv  Detail & Related papers  (2025-08-25T09:12:55Z)
• VideoMolmo: Spatio-Temporal Grounding Meets Pointing [66.19964563104385]
  VideoMolmo is a model tailored for fine-grained pointing of video sequences.<n>A novel temporal mask fusion employs SAM2 for bidirectional point propagation.<n>To evaluate the generalization of VideoMolmo, we introduce VPoMolS-temporal, a challenging out-of-distribution benchmark spanning five real-world scenarios.
  arXiv  Detail & Related papers  (2025-06-05T17:59:29Z)
• A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking [47.312955861553995]
  We propose Unified Video Fusion (UniVF), a novel framework for temporally coherent video fusion.<n>To support its development, we also introduce Video Fusion Benchmark (VF-Bench), the first comprehensive benchmark covering four video fusion tasks.
  arXiv  Detail & Related papers  (2025-05-26T11:45:10Z)
• Exploiting Inter-Sample Correlation and Intra-Sample Redundancy for Partially Relevant Video Retrieval [5.849812241074385]
  PRVR aims to retrieve the target video that is partially relevant to a text query. Existing methods coarsely align paired videos and text queries to construct the semantic space. We propose a novel PRVR framework to systematically exploit inter-sample correlation and intra-sample redundancy.
  arXiv  Detail & Related papers  (2025-04-28T09:52:46Z)
• DiVE: Efficient Multi-View Driving Scenes Generation Based on Video Diffusion Transformer [56.98400572837792]
  DiVE produces high-fidelity, temporally coherent, and cross-view consistent multi-view videos. These innovations collectively achieve a 2.62x speedup with minimal quality degradation.
  arXiv  Detail & Related papers  (2025-04-28T09:20:50Z)
• Towards Scalable Modeling of Compressed Videos for Efficient Action Recognition [6.168286187549952]
  We propose a hybrid end-to-end framework that factorizes learning across three key concepts to reduce inference cost by $330times$ versus prior art.<n> Experiments show that our method results in a lightweight architecture achieving state-of-the-art video recognition performance.
  arXiv  Detail & Related papers  (2025-03-17T21:13:48Z)
• CFSum: A Transformer-Based Multi-Modal Video Summarization Framework With Coarse-Fine Fusion [22.58710742780161]
  CFSum is a transformer-based multi-modal video summarization framework with coarse-fine fusion.<n> CFSum exploits video, text, and audio modal features as input, and incorporates a two-stage transformer-based feature fusion framework.
  arXiv  Detail & Related papers  (2025-03-01T06:13:13Z)
• RepVideo: Rethinking Cross-Layer Representation for Video Generation [53.701548524818534]
  We propose RepVideo, an enhanced representation framework for text-to-video diffusion models. By accumulating features from neighboring layers to form enriched representations, this approach captures more stable semantic information. Our experiments demonstrate that our RepVideo not only significantly enhances the ability to generate accurate spatial appearances, but also improves temporal consistency in video generation.
  arXiv  Detail & Related papers  (2025-01-15T18:20:37Z)
• Video Set Distillation: Information Diversification and Temporal Densification [68.85010825225528]
  Video textbfsets have two dimensions of redundancies: within-sample and inter-sample redundancies.<n>We are the first to study Video Set Distillation, which synthesizes optimized video data by addressing within-sample and inter-sample redundancies.
  arXiv  Detail & Related papers  (2024-11-28T05:37:54Z)
• LetsTalk: Latent Diffusion Transformer for Talking Video Synthesis [38.08071302910815]
  LetsTalk is a diffusion transformer that incorporates modular temporal and spatial attention mechanisms to merge multimodality and enhance spatial-temporal consistency. We propose a suitable solution according to the modality differences of image, audio, and video generation. Our experiments demonstrate that our approach generates temporally coherent and realistic videos with enhanced diversity and liveliness.
  arXiv  Detail & Related papers  (2024-11-24T04:46:00Z)
• Asynchronous Multimodal Video Sequence Fusion via Learning Modality-Exclusive and -Agnostic Representations [19.731611716111566]
  We propose a Multimodal fusion approach for learning modality-Exclusive and modality-Agnostic representations. We introduce a predictive self-attention module to capture reliable context dynamics within modalities. A hierarchical cross-modal attention module is designed to explore valuable element correlations among modalities. A double-discriminator strategy is presented to ensure the production of distinct representations in an adversarial manner.
  arXiv  Detail & Related papers  (2024-07-06T04:36:48Z)
• Vivid-ZOO: Multi-View Video Generation with Diffusion Model [76.96449336578286]
  New challenges lie in the lack of massive captioned multi-view videos and the complexity of modeling such multi-dimensional distribution. We propose a novel diffusion-based pipeline that generates high-quality multi-view videos centered around a dynamic 3D object from text.
  arXiv  Detail & Related papers  (2024-06-12T21:44:04Z)
• Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities [67.89368528234394]
  One of the main challenges of multimodal learning is the need to combine heterogeneous modalities. Video and audio are obtained at much higher rates than text and are roughly aligned in time. Our approach achieves the state-of-the-art on well established multimodal benchmarks, outperforming much larger models.
  arXiv  Detail & Related papers  (2023-11-09T19:15:12Z)
• Condensing a Sequence to One Informative Frame for Video Recognition [113.3056598548736]
  This paper studies a two-step alternative that first condenses the video sequence to an informative "frame" A valid question is how to define "useful information" and then distill from a sequence down to one synthetic frame. IFS consistently demonstrates evident improvements on image-based 2D networks and clip-based 3D networks.
  arXiv  Detail & Related papers  (2022-01-11T16:13:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.