Showing 2025Show all
2 papers · 1 filter
eess.AS2025
HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation
Sizhe Shan, Qiulin Li, Yutao Cui +5
Recent advances in video generation produce visually realistic content, yet the absence of synchronized audio severely compromises immersion. To address key challenges in video-to-…
cs.SD2025
Enhance Generation Quality of Flow Matching V2A Model via Multi-Step CoT-Like Guidance and Combined Preference Optimization
Haomin Zhang, Sizhe Shan, Haoyu Wang +4
Creating high-quality sound effects from videos and text prompts requires precise alignment between visual and audio domains, both semantically and temporally, along with step-by-s…