利用流匹配与解析维纳去噪器解决房间脉冲响应反问题
Solving Room Impulse Response Inverse Problems Using Flow Matching with Analytic Wiener Denoiser
AI总结:
本文提出RIRFlow框架,通过流匹配与解析维纳去噪器解决RIR反问题,无需训练数据,结合经典模型与生成推断提升反问题求解性能。
摘要:
房间脉冲响应(RIR)估计自然地出现为一类反问题,包括去噪和反卷积。尽管最近的方法通常依赖于监督学习或学习的生成先验,但这些方法需要大量训练数据且可能在训练分布之外泛化不佳。在本文中,我们提出了RIRFlow,一种无需训练的贝叶斯框架,用于解决RIR反问题中的流匹配。我们从RIR的统计结构中推导出一种流一致的解析先验,消除了对数据驱动先验的需求。具体来说,我们将RIR建模为具有指数衰减方差的高斯过程,这产生了一个闭式最小均方误差(MMSE)维纳去噪器。这个解析去噪器被整合到现有的基于流的反求解器中,其中反问题通过引导的后验采样来解决。此外,我们通过引导后验的局部高斯近似扩展了求解器,以解决非线性和非高斯反问题,并实验证明这种近似在实践中仍然有效。在不同反问题上的真实RIR实验显示了鲁棒性能,突显了将经典RIR模型与最近的基于流的生成推断相结合的有效性。
英文摘要:
Room impulse response (RIR) estimation naturally arises as a class of inverse problems, including denoising and deconvolution. While recent approaches often rely on supervised learning or learned generative priors, such methods require large amounts of training data and may generalize poorly outside the training distribution. In this work, we present RIRFlow, a training-free Bayesian framework for RIR inverse problems using flow matching. We derive a flow-consistent analytic prior from the statistical structure of RIRs, eliminating the need for data-driven priors. Specifically, we model RIR as a Gaussian process with exponentially decaying variance, which yields a closed-form minimum mean squared error (MMSE) Wiener denoiser. This analytic denoiser is integrated as a prior in an existing flow-based inverse solver, where inverse problems are solved via guided posterior sampling. Furthermore, we extend the solver to nonlinear and non-Gaussian inverse problems via a local Gaussian approximation of the guided posterior, and empirically demonstrate that this approximation remains effective in practice. Experiments on real RIRs across different inverse problems demonstrate robust performance, highlighting the effectiveness of combining a classic RIR model with the recent flow-based generative inference.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。