Research map / Video / Video generation
The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion
Yujin Jeong, Wonjeong Ryoo, Seunghyun Lee, Dabin Seo, Wonmin Byeon, Sangpil Kim, Jinkyu Kim
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 Temporal Attention Module to the audio encoder (ablation) | TPoS · Landscape | FVD: 483.76 -> 421.23 | Improved |
| add Temporal Attention Module to the audio encoder (ablation) | TPoS · Landscape | IS: 1.27 -> 1.49 | Improved |
| add Temporal Attention Module to the audio encoder (ablation) | TPoS · Landscape | CLIP score (audio-video): 0.1342 -> 0.1964 | Improved |
| add Temporal Attention Module (ablation) | TPoS · Landscape | CLIP score (text-video): 0.2370 -> 0.2436 | No clear effect |
| add Audio Semantic Guidance (SEGA-style) in diffusion (ablation) | TPoS · qualitative frames | content consistency | Improved |
| use audio instead of text for temporal changes | Stable Diffusion video generation · qualitative frames | temporal change quality | Improved |
| use TPoS instead of Sound2Sight/CCVS/StyleGAN-based baselines | audio-to-video generation · Landscape | FVD: 421.23 vs 494.28 (best baseline) | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- CCVS — CCVS: Context-aware Controllable Video Synthesis (NeurIPS 2021) · better on 3 of 3 shared results
- Sound2Sight — Sound2Sight: Generating Visual Dynamics from Sound and Context (ECCV 2020) · better on 2 of 2 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
- Read, Watch and Scream! Sound Generation from Text and Video (AAAI 2025 · similarity 0.89)
- Animate and Sound an Image (CVPR 2025 · similarity 0.89)
- Tri-Ergon: Fine-Grained Video-to-Audio Generation with Multi-Modal Conditions and LUFS Control (AAAI 2025 · similarity 0.88)
- Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation (AAAI 2024 · similarity 0.88)
- Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition (CVPR 2025 · similarity 0.87)
- Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners (CVPR 2024 · similarity 0.87)
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.
