Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Jun, Zeng, Xijuan, Qiang, Chunyu, Chen, Ruilong, Wang, Shiyao, Wang, Le, Zhou, Wangjing, Cai, Pengfei, Zhao, Jiahui, Li, Nan, Li, Zihan, Liang, Yuzhe, Wang, Xiaopeng, Zheng, Haorui, Wen, Ming, Yin, Kang, Wang, Yiran, Deng, Feng, Dong, Liang, Zhang, Chen, Zhang, Di, Gai, Kun
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2506.19774
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Tabla de Contenidos:
  • We propose Kling-Foley, a large-scale multimodal Video-to-Audio generation model that synthesizes high-quality audio synchronized with video content. In Kling-Foley, we introduce multimodal diffusion transformers to model the interactions between video, audio, and text modalities, and combine it with a visual semantic representation module and an audio-visual synchronization module to enhance alignment capabilities. Specifically, these modules align video conditions with latent audio elements at the frame level, thereby improving semantic alignment and audio-visual synchronization. Together with text conditions, this integrated approach enables precise generation of video-matching sound effects. In addition, we propose a universal latent audio codec that can achieve high-quality modeling in various scenarios such as sound effects, speech, singing, and music. We employ a stereo rendering method that imbues synthesized audio with a spatial presence. At the same time, in order to make up for the incomplete types and annotations of the open-source benchmark, we also open-source an industrial-level benchmark Kling-Audio-Eval. Our experiments show that Kling-Foley trained with the flow matching objective achieves new audio-visual SOTA performance among public models in terms of distribution matching, semantic alignment, temporal alignment and audio quality.