AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer
This addresses bottlenecks in video-to-audio synthesis for applications requiring precise acoustic control, such as Foley sound production, though it is incremental by building on existing V2A methods.
The paper tackled the problem of fine-grained sound synthesis in video-to-audio generation by proposing AC-Foley, which uses reference audio instead of text prompts to bypass semantic ambiguities, achieving state-of-the-art performance for Foley generation and competitive results without audio conditioning.
Existing video-to-audio (V2A) generation methods predominantly rely on text prompts alongside visual information to synthesize audio. However, two critical bottlenecks persist: semantic granularity gaps in training data, such as conflating acoustically distinct sounds under coarse labels, and textual ambiguity in describing micro-acoustic features. These bottlenecks make it difficult to perform fine-grained sound synthesis using text-controlled modes. To address these limitations, we propose AC-Foley, an audio-conditioned V2A model that directly leverages reference audio to achieve precise and fine-grained control over generated sounds. This approach enables fine-grained sound synthesis, timbre transfer, zero-shot sound generation, and improved audio quality. By directly conditioning on audio signals, our approach bypasses the semantic ambiguities of text descriptions while enabling precise manipulation of acoustic attributes. Empirically, AC-Foley achieves state-of-the-art performance for Foley generation when conditioned on reference audio, while remaining competitive with state-of-the-art video-to-audio methods even without audio conditioning.