Neural Acoustic Context Field: Rendering Realistic Room Impulse Response With Neural Fields
This work addresses the challenge of generating accurate audio simulations for applications like virtual reality, though it appears incremental by building on prior neural field methods.
The paper tackles the problem of synthesizing realistic room impulse responses (RIRs) for high-fidelity audio by proposing NACF, a neural field approach that incorporates acoustic contexts like geometry and material properties, resulting in notable performance improvements over existing methods.
Room impulse response (RIR), which measures the sound propagation within an environment, is critical for synthesizing high-fidelity audio for a given environment. Some prior work has proposed representing RIR as a neural field function of the sound emitter and receiver positions. However, these methods do not sufficiently consider the acoustic properties of an audio scene, leading to unsatisfactory performance. This letter proposes a novel Neural Acoustic Context Field approach, called NACF, to parameterize an audio scene by leveraging multiple acoustic contexts, such as geometry, material property, and spatial information. Driven by the unique properties of RIR, i.e., temporal un-smoothness and monotonic energy attenuation, we design a temporal correlation module and multi-scale energy decay criterion. Experimental results show that NACF outperforms existing field-based methods by a notable margin. Please visit our project page for more qualitative results.