Diff-V2M: A Hierarchical Conditional Diffusion Model with Explicit Rhythmic Modeling for Video-to-Music Generation

• URL: http://arxiv.org/abs/2511.09090v1
• Date: Thu, 13 Nov 2025 01:31:12 GMT
• Title: Diff-V2M: A Hierarchical Conditional Diffusion Model with Explicit Rhythmic Modeling for Video-to-Music Generation
• Authors: Shulei Ji, Zihao Wang, Jiaxing Yu, Xiangyuan Yang, Shuyu Li, Songruoyao Wu, Kejun Zhang,
• Abstract summary: Video-to-music (V2M) generation aims to create music that aligns with visual content.<n>We propose Diff-V2M, a general V2M framework based on a hierarchical conditional diffusion model.<n>For rhythm modeling, we begin by evaluating several rhythmic representations, including low-resolution mel-spectrograms, tempograms, and onset detection functions (ODF)
• Score: 26.273309051211204
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video-to-music (V2M) generation aims to create music that aligns with visual content. However, two main challenges persist in existing methods: (1) the lack of explicit rhythm modeling hinders audiovisual temporal alignments; (2) effectively integrating various visual features to condition music generation remains non-trivial. To address these issues, we propose Diff-V2M, a general V2M framework based on a hierarchical conditional diffusion model, comprising two core components: visual feature extraction and conditional music generation. For rhythm modeling, we begin by evaluating several rhythmic representations, including low-resolution mel-spectrograms, tempograms, and onset detection functions (ODF), and devise a rhythmic predictor to infer them directly from videos. To ensure contextual and affective coherence, we also extract semantic and emotional features. All features are incorporated into the generator via a hierarchical cross-attention mechanism, where emotional features shape the affective tone via the first layer, while semantic and rhythmic features are fused in the second cross-attention layer. To enhance feature integration, we introduce timestep-aware fusion strategies, including feature-wise linear modulation (FiLM) and weighted fusion, allowing the model to adaptively balance semantic and rhythmic cues throughout the diffusion process. Extensive experiments identify low-resolution ODF as a more effective signal for modeling musical rhythm and demonstrate that Diff-V2M outperforms existing models on both in-domain and out-of-domain datasets, achieving state-of-the-art performance in terms of objective metrics and subjective comparisons. Demo and code are available at https://Tayjsl97.github.io/Diff-V2M-Demo/.

Related papers

• DINOv2 Driven Gait Representation Learning for Video-Based Visible-Infrared Person Re-identification [30.593882551803855]
  Video-based Visible-Infrared person re-identification (VVI-ID) aims to retrieve the same pedestrian across visible and infrared modalities from modality.<n>To address these challenges, we propose a Gait Representation Learning framework that leverages the rich visual priors of DINOv2 to learn gait features complementary to appearance cues.<n>Specifically, we introduce a Semantic-Aware Silhouette and Gait Learning (GL) model, which generates and enhances silhouette representations with general-purpose semantic priors from DINOv2.
  arXiv  Detail & Related papers  (2025-11-06T11:21:13Z)
• LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model [18.564067196226436]
  We propose a text-to-motion diffusion model that incorporates dual-path anchoring to enhance semantic alignment.<n>LUMA achieves state-of-the-art performance, with FID scores of 0.035 and 0.123, respectively.
  arXiv  Detail & Related papers  (2025-09-29T17:58:28Z)
• High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling [65.02357548201188]
  We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning.<n>Our framework operates by synthesizing the desired separated sound spectrograms directly from a noise distribution, conditioned concurrently on the mixed audio input and associated visual information.
  arXiv  Detail & Related papers  (2025-09-26T08:46:00Z)
• StableDub: Taming Diffusion Prior for Generalized and Efficient Visual Dubbing [63.72095377128904]
  The visual dubbing task aims to generate mouth movements synchronized with the driving audio.<n>Audio-only driving paradigms inadequately capture speaker-specific lip habits.<n>Blind-inpainting approaches produce visual artifacts when handling obstructions.
  arXiv  Detail & Related papers  (2025-09-26T05:23:31Z)
• Feature Hallucination for Self-supervised Action Recognition [37.20267786858476]
  We propose a deep translational action recognition framework that enhances recognition accuracy by jointly predicting action concepts and auxiliary features from RGB video frames.<n>Our framework achieves state-of-the-art performance on multiple benchmarks, including Kinetics-400, Kinetics-600, and Something-Something V2, demonstrating its effectiveness in capturing fine-grained action dynamics.
  arXiv  Detail & Related papers  (2025-06-25T11:50:23Z)
• MF2Summ: Multimodal Fusion for Video Summarization with Temporal Alignment [5.922172844641853]
  This paper introduces MF2Summ, a novel video summarization model based on multimodal content understanding.<n>MF2Summ employs a five-stage process: feature extraction, cross-modal attention interaction, feature fusion, segment prediction, and key shot selection.<n> Experimental results on the SumMe and TVSum datasets demonstrate that MF2Summ achieves competitive performance.
  arXiv  Detail & Related papers  (2025-06-12T07:32:51Z)
• 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)
• MotionRAG-Diff: A Retrieval-Augmented Diffusion Framework for Long-Term Music-to-Dance Generation [10.203209816178552]
  MotionRAG-Diff is a hybrid framework that integrates Retrieval-Augmented Generation and diffusion-based refinement.<n>Our method introduces three core innovations.<n>It achieves state-of-the-art performance in motion quality, diversity, and music-motion synchronization accuracy.
  arXiv  Detail & Related papers  (2025-06-03T09:12:48Z)
• Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition [57.74076383449153]
  We propose a novel dual-stream framework for event stream-based pattern recognition via differentiated fusion, termed EFV++. It models two common event representations simultaneously, i.e., event images and event voxels. We achieve new state-of-the-art performance on the Bullying10k dataset, i.e., $90.51%$, which exceeds the second place by $+2.21%$.
  arXiv  Detail & Related papers  (2024-06-27T02:32:46Z)
• Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching [51.70360630470263]
  Video-to-audio (V2A) generation aims to synthesize content-matching audio from silent video.<n>We propose Frieren, a V2A model based on rectified flow matching.<n>Experiments indicate that Frieren achieves state-of-the-art performance in both generation quality and temporal alignment.
  arXiv  Detail & Related papers  (2024-06-01T06:40:22Z)
• From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos [88.08209394979178]
  Dynamic facial expression recognition (DFER) in the wild is still hindered by data limitations. We introduce a novel Static-to-Dynamic model (S2D) that leverages existing SFER knowledge and dynamic information implicitly encoded in extracted facial landmark-aware features.
  arXiv  Detail & Related papers  (2023-12-09T03:16:09Z)
• Taming Diffusion Models for Music-driven Conducting Motion Generation [1.0624606551524207]
  This paper presents Diffusion-Conductor, a novel DDIM-based approach for music-driven conducting motion generation. We propose a random masking strategy to improve the feature robustness, and use a pair of geometric loss functions to impose additional regularizations. We also design several novel metrics, including Frechet Gesture Distance (FGD) and Beat Consistency Score (BC) for a more comprehensive evaluation of the generated motion.
  arXiv  Detail & Related papers  (2023-06-15T03:49:24Z)
• Slow-Fast Visual Tempo Learning for Video-based Action Recognition [78.3820439082979]
  Action visual tempo characterizes the dynamics and the temporal scale of an action. Previous methods capture the visual tempo either by sampling raw videos with multiple rates, or by hierarchically sampling backbone features. We propose a Temporal Correlation Module (TCM) to extract action visual tempo from low-level backbone features at single-layer remarkably.
  arXiv  Detail & Related papers  (2022-02-24T14:20:04Z)

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.