# MMAudioReverbs: Video-Guided Acoustic Modeling for Dereverberation and Room Impulse Response Estimation

arXiv: https://arxiv.org/abs/2605.00431 · HTML: https://mlsanity.com/paper/2605.00431/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 15 references that are in the map.
- First posted on arXiv 1 May 2026.

## Builds on (most cited first, 14 of 14)

- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis](https://mlsanity.com/paper/2412.15322/) (2024)
- [SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning](https://mlsanity.com/paper/2206.08312/) (2022)
- [Learning Neural Acoustic Fields](https://mlsanity.com/paper/2204.00628/) (2022)
- [Video-Guided Foley Sound Generation with Multimodal Controls](https://mlsanity.com/paper/2411.17698/) (2024)
- [Few-Shot Audio-Visual Learning of Environment Acoustics](https://mlsanity.com/paper/2206.04006/) (2022)
- [Visual Acoustic Matching](https://mlsanity.com/paper/2202.06875/) (2022)
- [Image2Reverb: Cross-Modal Reverb Impulse Response Synthesis](https://mlsanity.com/paper/2103.14201/) (2021)
- [Learning Audio-Visual Dereverberation](https://mlsanity.com/paper/2106.07732/) (2021)
- [AV-RIR: Audio-Visual Room Impulse Response Estimation](https://mlsanity.com/paper/2312.00834/) (2023)
- [Filtered Noise Shaping for Time Domain Room Impulse Response Estimation From Reverberant Speech](https://mlsanity.com/paper/2107.07503/) (2021)
- [Towards Improved Room Impulse Response Estimation for Speech Recognition](https://mlsanity.com/paper/2211.04473/) (2022)
- [How Would It Sound? Material-Controlled Multimodal Acoustic Profile Generation for Indoor Scenes](https://mlsanity.com/paper/2508.02905/) (2025)
- [MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation](https://mlsanity.com/paper/2510.09065/) (2025)

## Abstract (arXiv)

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.