FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds

Yiming Zhang¹ Yicheng Gu² Yanhong Zeng^{1 †} Zhening Xing¹ Yuancheng Wang²
Zhizheng Wu² Kai Chen<sup>1 †

1</sup>Shanghai AI Laboratory     ²Chinese University of Hong Kong, Shenzhen     †Corresponding author

2-minute Video

FoleyCrafter is a text-based video-to-audio generation framework which can generate high-quality audios that are semantically relevant and temporally synchronized with the input videos.

Abstract

We study Neural Foley, the automatic generation of high-quality sound effects synchronizing with videos, enabling an immersive audio-visual experience. Despite its wide range of applications, existing approaches encounter limitations when it comes to simultaneously synthesizing high-quality and video-aligned (i.e.,, semantic relevant and temporal synchronized) sounds. To overcome these limitations, we propose FoleyCrafter, a novel framework that leverages a pre-trained text-to-audio model to ensure high-quality audio generation. FoleyCrafter comprises two key components: the semantic adapter for semantic alignment and the temporal controller for precise audio-video synchronization. The semantic adapter utilizes parallel cross-attention layers to condition audio generation on video features, producing realistic sound effects that are semantically relevant to the visual content. Meanwhile, the temporal controller incorporates an onset detector and a timestamp based adapter to achieve precise audio-video alignment. One notable advantage of FoleyCrafter is its compatibility with text prompts, enabling the use of text descriptions to achieve controllable and diverse video-to-audio generation according to user intents. We conduct extensive quantitative and qualitative experiments on standard benchmarks to verify the effectiveness of FoleyCrafter. Models and codes are available at Github.

Method

Gallery

More new interesting cases are at link: and under the tag #FoleyCrafter in twitter!

BibTex