Explicit Context-Driven Neural Acoustic Modeling for High-Fidelity RIR Generation

2025/09/18 by Si Chen, Si, Chen, Qiong Wu +5
Computer Science · Neuroscience · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Face recognition and analysis #Generative Adversarial Networks and Image Synthesis #Hearing Loss and Rehabilitation #Machine Learning (cs.LG) #Sound (cs.SD)

paper · pdf · doi:10.48550/arxiv.2509.15210

openalex publication_date 2025/09/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Realistic sound simulation plays a critical role in many applications. A key element in sound simulation is the room impulse response (RIR), which characterizes how sound propagates within a given space. Recent studies have applied neural implicit methods to learn RIR using context information collected from the environment, such as scene images. However, these approaches do not effectively leverage explicit geometric information from the environment. To further exploit neural implicit models with direct geometric features, we present MiNAF, which queries a rough room mesh at given locations and extracts distance distributions as an explicit representation of local context. Our approach demonstrates that incorporating explicit local geometric features can better guide the model in generating more accurate RIR predictions. Through comparisons with conventional and state-of-the-art methods, we show that MiNAF performs competitively across various evaluation metrics.

Citations

• VGGT: Visual Geometry Grounded Transformer
• NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields
• Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes
• 3D Visibility-aware Generalizable Neural Radiance Fields for Interacting Hands
• DUSt3R: Geometric 3D Vision Made Easy
• ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field
• Neural Acoustic Context Field: Rendering Realistic Room Impulse Response With Neural Fields
• Neuralangelo: High-Fidelity Neural Surface Reconstruction
• Few-shot Neural Radiance Fields Under Unconstrained Illumination
• AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis
• Few-Shot Audio-Visual Learning of Environment Acoustics
• Learning Neural Acoustic Fields
• Deep Impulse Responses: Estimating and Parameterizing Filters with Deep Networks
• Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs
• RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs
• Image2Reverb: Cross-Modal Reverb Impulse Response Synthesis
• KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs
• Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance\n Fields
• FastNeRF: High-Fidelity Neural Rendering at 200FPS
• Position Information in Transformers: An Overview
• Position Information in Transformers: An Overview
• pixelNeRF: Neural Radiance Fields from One or Few Images
• 3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics
• The Replica Dataset: A Digital Replica of Indoor Spaces
• GANSynth: Adversarial Neural Audio Synthesis
• Adam: A Method for Stochastic Optimization
• Image method for efficiently simulating small-room acoustics

Related

• Neural Acoustic Context Field: Rendering Realistic Room Impulse Response With Neural Fields
• Hearing Anywhere in Any Environment
• Spatial Interpolation of Room Impulse Responses based on Deeper Physics-Informed Neural Networks with Residual Connections
• Data Augmentation Using Neural Acoustic Fields With Retrieval-Augmented Pre-training
• Learning Neural Acoustic Fields