让声学模拟可微分,实现材料属性的梯度优化
Differentiable Acoustic Radiance Transfer
- 基于可微分声学辐射传输,建模表面能量交换
- 稀疏测量下预测性能优于传统方法和神经网络
- 保持简单透明,适合需要可解释性的声学研究
几何声学是高效的房间声学建模框架,由经典时变渲染方程描述。声学辐射传输(ART)通过离散化求解该方程,以灵活材质属性建模表面单元间的时间与方向依赖能量交换。本文提出DART,一种高效且可微分的ART实现,支持材料属性的梯度优化。我们在一个简化的声场学习任务上评估DART,目标是为新的声源-接收器配置预测能量响应。实验表明,相较于现有信号处理与神经网络基线,DART在稀疏测量条件下泛化能力更强,同时保持方法简洁与完全可解释性。代码已开源。
原文摘要 · Abstract (English)
Geometric acoustics is an efficient framework for room acoustics modeling, governed by the canonical time-dependent rendering equation. Acoustic radiance transfer (ART) solves the equation by discretization, modeling time- and direction-dependent energy exchange between surface patches with flexible material properties. We introduce DART, an efficient, differentiable implementation of ART that enables gradient-based optimization of material properties. We evaluate DART on a simpler variant of acoustic field learning that aims to predict energy responses for novel source-receiver configurations. Experimental results demonstrate that DART generalizes better under sparse measurement scenarios than existing signal processing and neural network baselines, while maintaining simplicity and full interpretability. We open-source our implementation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。