ECCV Paper: Step-by-Step Video-to-Audio Synthesis via Negative Guidance
mittu1204 · x · 2026-08-31
Inspired by traditional Foley workflows, this paper proposes a step-by-step video-to-audio (V2A) method allowing incremental sound event authoring. To avoid costly multi-reference datasets, each step uses negative guidance to suppress sounds from previous tracks. The guidance model is fine-tuned on non-overlapping segments of standard single-reference datasets, leveraging acoustic context while staying visually grounded. Evaluations show improved sound separability and composite audio quality.
More from Multimodal
- Pollo AI launches Recast video restyling, 60% off for launch — SimplyAnnisa · 2026-10-16
- Tripo hosts first world-building hackathon in SF with World Labs and Runway talks — mhdfaran · 2026-10-16
- Kling 4.0 boosts text-to-video with character consistency and lip sync — CurieuxExplorer · 2026-10-16
- 5.8M-param Speech Event Detector adds laughs, breaths and背景 sounds to Whisper transcripts — Ayush Kumar Bar · 2026-10-16
- Huawei's SUPRA-Tex turns one image into relightable 3D materials with WYSIWYG fidelity — Chen Yang · 2026-10-16
- Giant Michael Jackson AI fashion images show the power of extreme proportions — OVolosin82152 · 2026-10-16