Research map / Video / Video generation
Audio-Guided Video Scene Editing
Kaixin Shen, Ruijie Quan, Linchao Zhu, Dong Zheng, Jun Hua Xiao, Yi Yang
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-aware audio semantic injection (TASI) (ablation) | AudioScenic · Ablation (Waterfall audio) | Sem-A: 75% drop; 0.25 -> 1.0 | Improved |
| add TASI (ablation) | AudioScenic · Ablation (Waterfall audio) | Temp-S: 25.11 -> 29.61 | Improved |
| add SceneMasker (ablation) | AudioScenic · Ablation (Waterfall audio) | SSIM: 0.8863 -> 0.9512; 6.82% drop of SSIM without it | Improved |
| add SceneMasker (ablation) | AudioScenic · Ablation (Waterfall audio) | Temp-S: 29.41 -> 29.61 | No clear effect |
| add Frequency Fuser (ablation) | AudioScenic · Ablation (Waterfall audio) | Temp-S: 28.18 -> 29.61; 4.83% drop of Temp-S without it | Improved |
| add Frequency Fuser (ablation) | AudioScenic · Ablation (Waterfall audio) | SSIM: 0.9467 -> 0.9512 | No clear effect |
| use audio-driven AudioScenic instead of text-driven Tune-A-Video, FateZero, VideoP2P | Stable Diffusion video editing · DAVIS/Audioset (10 samples) | Sem-A: 0.525 -> 0.825 | Improved |
| AudioScenic vs text-driven baselines on foreground preservation | Stable Diffusion video editing · DAVIS/Audioset (10 samples) | SSIM: 0.8944 -> 0.9403 | Improved |
| AudioScenic vs text-driven baselines on temporal consistency | Stable Diffusion video editing · DAVIS/Audioset (10 samples) | Temp-S: 28.48 -> 29.31 | 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.
- VideoP2P — Video-P2P: Video Editing with Cross-attention Control (CVPR 2024) · better on 3 of 3 shared results
- Tune-A-Video — Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation (ICCV 2023) · better on 3 of 3 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
- SoundBrush: Sound as a Brush for Visual Scene Editing (AAAI 2025 · similarity 0.87)
- AVENUE: Audio-Video Editing Understanding and Evaluation (NeurIPS 2026 · similarity 0.86)
- Learning to Highlight Audio by Watching Movies (CVPR 2025 · similarity 0.86)
- Audio-Sync Video Generation with Multi-Stream Temporal Control (NeurIPS 2025 · similarity 0.85)
- Tri-Ergon: Fine-Grained Video-to-Audio Generation with Multi-Modal Conditions and LUFS Control (AAAI 2025 · similarity 0.84)
- ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing (NeurIPS 2026 · similarity 0.84)
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.
