AI Paper Atlas

Research map / Video / Video generation

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

Shulei Ji, Zihao Wang, Jiaxing Yu, Xiangyuan Yang, Shuyu Li, Songruoyao Wu, Kejun Zhang

AAAI 2026 · Video › Video generation · approach: Video-to-audio synthesis · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use low-resolution ODF instead of low-res mel-spectrogram as rhythm representation (ablation)Diff-V2M · Mixed test setFAD: 2.0376 -> 2.0175Improved
use low-resolution ODF instead of tempogram (ablation)Diff-V2M · Mixed test setFAD: 2.3163 -> 2.0175Improved
add post-attention FiLM with feature selection over weighted fusion (ablation)Diff-V2M · Mixed test setFAD: 2.3625 -> 1.5175Improved
apply FiLM after rather than before attention (ablation)Diff-V2M · Mixed test setFAD: 2.0812 -> 2.1340No clear effect
add rhythmic features (ablation)Diff-V2M · Mixed test setFAD: 1.8264 -> 1.5175Improved
add rhythmic features (ablation)Diff-V2M · Mixed test setImageBind score: 0.1893 -> 0.1812Hurt
add emotional features (ablation)Diff-V2M · Mixed test setFAD: 1.6761 -> 1.5175Improved
add visual rhythm inputs (scene onset, visual beats) to rhythm predictor (ablation)Diff-V2M · Mixed test setFAD: 2.2177 -> 1.5175Improved
jointly train rhythm predictor and generator (ablation)Diff-V2M · Mixed test setFAD: 1.8787 -> 1.5175Improved
jointly train rhythm predictor and generator (ablation)Diff-V2M · V2M-BenchFAD: 3.3245 -> 1.7612Improved
add scheduled conditioning (ablation)Diff-V2M · Mixed test setFAD: 1.6159 -> 1.5175Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy