Research map / Video / Video generation
Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity
Santiago Pascual, Chunghsin YEH, Ioannis Tsiamas, Joan Serrà
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add S3D alignment features (SparseSync-pretrained) to CLIP conditioning via AdaLN (ablation) | MaskVAT AdaLN · VGGSound-Test | SparseSync offset: 0.60 -> 0.43 | Improved |
| add S3D alignment features to CLIP conditioning via AdaLN (ablation) | MaskVAT AdaLN · VGGSound-Test | Novelty score: 0.05 -> 0.16 | Improved |
| add S3D features to CLIP conditioning (ablation) | MaskVAT AdaLN · VGGSound-Test | FAD: 3.83 -> 3.39 | Improved |
| use seq2seq cross-attention with BEATs distillation losses instead of AdaLN (ablation) | MaskVAT · VGGSound-Test | WaveCLIP: 0.50 -> 0.55 | Improved |
| use seq2seq instead of AdaLN with S3D (ablation) | MaskVAT · VGGSound-Test | SparseSync offset: 0.43 -> 0.63 | Hurt |
| use full-band DAC codec instead of baselines' lossy low-band pipelines | MaskVAT · VGGSound-Test | FAD: 1.51 vs 0.84 | Hurt |
| apply bandwidth extension to baselines | SpecVQGAN · VGGSound-Test | FDD: 0.26 -> 0.42 | Hurt |
| use MaskVAT Hybrid instead of V2A-Mapper in human evaluation | V2A-Mapper · VGGSound-sparse subjective test | Alignment MOS: 2.12 -> 3.81 | Improved |
| use MaskVAT Hybrid instead of V2A-Mapper | V2A-Mapper · VGGSound subjective test | Fidelity MOS: 3.00 -> 2.76 | No clear effect |
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.
- Diff-Foley — Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models (NeurIPS 2023) · better on 5 of 5 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
- Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows (CVPR 2025 · similarity 0.89)
- Frieren: Efficient Video-to-Audio Generation Network with Rectified Flow Matching (NeurIPS 2024 · similarity 0.89)
- VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation (CVPR 2025 · similarity 0.89)
- From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation (ICML 2024 · similarity 0.88)
- Animate and Sound an Image (CVPR 2025 · similarity 0.88)
- Audio-Sync Video Generation with Multi-Stream Temporal Control (NeurIPS 2025 · similarity 0.88)
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.
