Research map / Video / Video generation
FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds
Yiming Zhang, Yicheng Gu, Yanhong Zeng, Zhening Xing, Y. Q. Wang, Zhizheng Wu, Bin Liu, Kai Chen
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 semantic adapter instead of captioner-generated text prompts (ablation) | FoleyCrafter · AVSync15 | FID: 67.40 -> 36.80 | Improved |
| add semantic adapter instead of captioner-generated text prompts (ablation) | FoleyCrafter · AVSync15 | CLIP score: 9.177 -> 11.94 | Improved |
| add semantic adapter instead of captioner-generated text prompts (ablation) | FoleyCrafter · AVSync15 | MKL: 2.331 -> 1.497 | Improved |
| add semantic adapter instead of feeding visual embedding directly (ablation) | FoleyCrafter · AVSync15 | FID: 99.77 -> 36.80 | Improved |
| fine-tune UNet when feeding visual embedding directly (ablation) | Visual embedding baseline · AVSync15 | FID: 99.77 -> 95.78 | No clear effect |
| add temporal controller to semantic adapter (ablation) | FoleyCrafter · AVSync15 | Onset ACC: 26.65 -> 28.48 | Improved |
| add temporal controller to semantic adapter (ablation) | FoleyCrafter · AVSync15 | Onset AP: 63.20 -> 68.14 | Improved |
| compare FoleyCrafter with Diff-Foley | FoleyCrafter · AVSync15 | FID: 65.77 -> 36.80 | Improved |
| compare FoleyCrafter with V2A-Mapper | FoleyCrafter · VGGSound | FID: 24.16 -> 19.67 | Improved |
Later papers that compared with this method
2 later accepted papers report FoleyCrafter as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- HarmoniDPO: Video-guided Audio Generation via Preference-Optimized Diffusion (IJCV 2026 · better on 10 of 10 shared results)
- SALSA-V: Shortcut-Augmented Long-form Synchronized Audio from Videos (ICML 2026 · better on 2 of 2 shared results)
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 8 of 8 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 0.90)
- MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis (CVPR 2025 · similarity 0.89)
- Audio-Sync Video Generation with Multi-Stream Temporal Control (NeurIPS 2025 · similarity 0.88)
- Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation (AAAI 2024 · similarity 0.88)
- SonicVisionLM: Playing Sound with Vision Language Models (CVPR 2024 · similarity 0.87)
- Tri-Ergon: Fine-Grained Video-to-Audio Generation with Multi-Modal Conditions and LUFS Control (AAAI 2025 · 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.
