Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark

TL;DR

This paper introduces the Real Acoustic Fields (RAF) dataset, a comprehensive real-world audio-visual room acoustics dataset with high-quality impulse responses, multi-view images, and pose data, enabling improved evaluation and development of neural acoustic models.

Contribution

The paper provides the first densely captured real-world acoustic dataset with multi-modal data, and evaluates existing models, proposing enhancements and a sim2real approach for better real-world performance.

Findings

Existing models perform better with real-world data after fine-tuning.

Incorporating visual data improves neural acoustic field models.

Pre-training on simulated data and fine-tuning enhances few-shot learning.

Abstract

We present a new dataset called Real Acoustic Fields (RAF) that captures real acoustic room data from multiple modalities. The dataset includes high-quality and densely captured room impulse response data paired with multi-view images, and precise 6DoF pose tracking data for sound emitters and listeners in the rooms. We used this dataset to evaluate existing methods for novel-view acoustic synthesis and impulse response generation which previously relied on synthetic data. In our evaluation, we thoroughly assessed existing audio and audio-visual models against multiple criteria and proposed settings to enhance their performance on real-world data. We also conducted experiments to investigate the impact of incorporating visual data (i.e., images and depth) into neural acoustic field models. Additionally, we demonstrated the effectiveness of a simple sim2real approach, where a model is pre-trained with simulated data and fine-tuned with sparse real-world data, resulting in significant improvements in the few-shot learning approach. RAF is the first dataset to provide densely captured room acoustic data, making it an ideal resource for researchers working on audio and audio-visual neural acoustic field modeling techniques. Demos and datasets are available on our project page: https://facebookresearch.github.io/real-acoustic-fields/