MMAudioReverbs: Video-Guided Acoustic Modeling for Dereverberation and Room Impulse Response Estimation
For researchers in audio-visual processing, this work shows that existing V2A models can be repurposed for room-acoustic tasks with minimal data, but the improvements are incremental and lack quantitative comparisons to specialized methods.
The paper proposes MMAudioReverbs, a unified framework for dereverberation and room impulse response estimation that fine-tunes a pretrained video-to-audio model on a small dataset without architectural changes. Results show that audio and visual cues each have advantages depending on the type of room acoustics, demonstrating that foundation V2A models can be used for physically grounded room-acoustic analysis.
Although recent video-to-audio (V2A) models excelled at synthesizing semantically plausible sounds from visual inputs, they do not explicitly model room-acoustic effects such as reverberation or room impulse responses (RIRs), and thus offer limited controllability over these effects. However, we hypothesize that such V2A models implicitly have semantic knowledge of the relationship between spatial audio and the corresponding vision cues. In this paper, we revisit a V2A model for the sake of the above, and propose the way to utilize the pretrained model as prior for physically grounded room-acoustic processing. Based on one of the state-of-the-art V2A models, MMAudio, we propose MMAudioReverbs that is a unified framework dealing with i) dereverberation and ii) room impulse response (RIR) estimation without network architectural modification, and fine-tuned on a small dataset. Experimental results showed that audio and visual cues respectively have advantage depending on the type of physical room acoustics. It implies that foundation V2A models can be used for physically grounded room-acoustic analysis.