Research map / Video / Video generation
Sound-Guided Semantic Video Generation
Seung Hyun Lee, Gyeongrok Oh, Wonmin Byeon, Chanyoung Kim, Won Jeong Ryoo, Sang Ho Yoon, Hyunjun Cho, Jihyun Bae, Jinkyu Kim, Sangpil 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 CLIP loss to inversion (ablation) | StyleGAN inversion · LHQ inversion | LPIPS: 0.468 -> 0.432 | Improved |
| add CLIP loss to inversion (ablation) | StyleGAN inversion · LHQ inversion | MSE: 0.070 -> 0.048 | Improved |
| add LPIPS loss to inversion (ablation) | StyleGAN inversion · LHQ inversion | LPIPS: 0.648 -> 0.468 | Improved |
| add LPIPS loss to inversion (ablation) | StyleGAN inversion · LHQ inversion | MSE: 0.052 -> 0.070 | Hurt |
| add sound input (ablation) | video generator · Landscape | FVD: 305.91 -> 291.88 | Improved |
| add sound input (ablation) | video generator · Landscape | IS: 1.68 -> 1.82 | Improved |
| add sound input (ablation) | video generator · Sub-URMP | FVD: 272.27 -> 271.03 | No clear effect |
| add sound input (ablation) | video generator · Sub-URMP | IS: 2.99 -> 3.05 | No clear effect |
| use StyleGAN-based generator instead of Sound2Sight | video generator · Landscape | FVD: 311.55 -> 291.88 | Improved |
| add multiple recurrent blocks (coarse, mid, fine) (ablation) | video generator · Landscape (qualitative) | style control | 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 6 of 6 shared results
- Sound2Sight — Sound2Sight: Generating Visual Dynamics from Sound and Context (ECCV 2020) · better on 6 of 6 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
- Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation (AAAI 2024 · similarity 0.88)
- Read, Watch and Scream! Sound Generation from Text and Video (AAAI 2025 · similarity 0.88)
- Tri-Ergon: Fine-Grained Video-to-Audio Generation with Multi-Modal Conditions and LUFS Control (AAAI 2025 · similarity 0.86)
- SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation (ICLR 2025 · similarity 0.86)
- VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation (CVPR 2025 · similarity 0.86)
- Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners (CVPR 2024 · similarity 0.86)
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.
