Scene-adaptive immersive audio rendering requires rapid estimation of acoustic parameters that reflect the surrounding environment. For repeated runtime scene updates, performing a detailed geometric-acoustic simulation for every update can be computationally costly. We present Point2Acoustic, a learning-based framework for direct estimation of six-band reverberation time (RT60) and reverberant-to-direct ratio (RDR) from 3D scene geometry and acoustic material properties. Each scene is represented by a surface-sampled point cloud with spatial coordinates and frequency-dependent absorption and scattering coefficients, and encoded using PointNet or PointNet++. We train and evaluate the framework on a synthetic furnished-room dataset with varied geometry and acoustic materials, using geometric-acoustic simulation to obtain reference targets. Point2Acoustic achieves accurate multi-band prediction with millisecond-scale inference, and ablation results indicate that explicit global room descriptors and semantic surface labels provide no consistent benefit. The proposed formulation supports efficient scene-adaptive acoustic rendering in extended reality (XR).
Figures & tables
Figure 1: Overview of the Point2Acoustic training framework. Surface-sampled 3D scenes are encoded by PointNet or PointNet++ and mapped to six-band RT60 and RDR estimates using simulation-derived training targets.
RT60
RDR
Method
MAE ↓
R2↑
MAE ↓
R2↑
Params.
Runtime
(s)
(dB)
(M)
/scene
Sabine
0.1511
0.8942
1.4645
0.6798
–
–
Eyring
0.1542
0.8873
1.5557
0.6956
–
–
MLP
0.1316
0.9299
1.1295
0.8688
0.020
0.0022 ms
PN
0.1118
0.9436
1.1145
0.8717
0.473
0.927 ms
Table 1: Prediction accuracy and computational efficiency of the evaluated methods. PN and PN++ denote Point2Acoustic-PN and Point2Acoustic-PN++, respectively.
Figure 2: Prediction error across the reference acoustic-parameter range. MAE is computed within seven equal-count bins over the six octave bands and 500 test scenes.
RT60
RDR
Features
MAE (s) ↓
R2↑
MAE (dB) ↓
R2↑
Full
0.0979
0.9612
1.1395
0.8708
No global
0.0956
0.9628
1.0986
0.8766
No semantic
0.0941
0.9652
1.1194
0.8718
XYZ + material
0.0916
0.9661
1.1210
0.8733
No material
0.4707
0.1532
3.3294
0.2334
Table 2: Feature ablation of Point2Acoustic-PN++. Material denotes per-point six-band absorption and scattering coefficients.
Figure 3: Robustness to coordinate noise and point dropout. Results show the change in test R2 from clean input; error bars denote mean ± standard deviation over five trials.
Impact sound rendering synthesizes the sound produced when a 3D object is struck, but practical renderers often rely on fixed material presets such as wood, plastic, or steel. These presets limit the range of impact sounds a renderer can express, while manually adjusting the underlying material parameters remains difficult without expertise in material acoustics. We therefore study inverse impact sound rendering: predicting material parameters from a reference impact sound so that a simulator can recreate a similar material response. To support this task, we introduce ImpactMat, a dataset and benchmark of single and blended material impact sounds paired with ground-truth material parameters. We further propose a feed-forward model that predicts these parameters from one or more recordings, using blended materials to learn smooth transitions between material types. Experiments show that our method outperforms competitive baselines and enables re-rendering from real recordings without manual parameter tuning. The project page is available https://material-from-impact.github.io/material-from-impact/.
Hyebin Cho, Bumsoo Kim, Joon Son Chung
Korea Advanced Institute of Science and Technology, South Korea · Chung-Ang University, South Korea
Machine-learnt models are increasingly used to predict ISO 3382-1 room acoustic parameters at unmeasured seats from sparse measurements, with reported coefficients of determination frequently above 0.85. This paper shows that such figures are often determined by the evaluation protocol rather than by the model. Using a multi-condition measurement campaign in a 264-seat conference hall and a 180-seat concert hall, three model families were evaluated under a factorial protocol ablation: validation splits either row-based or grouped by receiver position, and inputs either including measured-at-test quantities (the target position's impulse response, co-located parameter measurements, position identifiers) or restricted to source-receiver geometry and environmental state. Row-based splits with measured-at-test inputs reproduce the high reported accuracies (mean R^2 of 0.81 for the core parameters); grouped splits with deployment-consistent inputs reduce these to 0.09-0.60 and reorder the apparent difficulty of parameter classes. Access to the target's own impulse response at test time reproduces the high accuracy of the row-based folds but provides no benefit under grouped folds. The row-based figure reflects condition interpolation at the measured positions rather than transferable acoustic information. Under the deployment-consistent protocol the spread between Random Forest, the hybrid network, and inverse-distance weighting is several times smaller than the spread between protocols for a fixed model; the learnt models retain a measurable advantage for sound strength and reverberation time, and the high accuracy of the original pipelines re-emerges as condition interpolation at measured positions, a distinct and operationally useful task. A reporting checklist operationalises the findings.
Ak\in Oktav
Vibration and Acoustics Laboratory (VAL) and Department of Mechanical Engineering, Alanya Alaaddin Keykubat University, 07425, Antalya, Türkiye
Image-source-method (ISM)-based room impulse response (RIR) simulation is a useful and physically interpretable tool for acoustic scene modeling, but full-order ISM becomes computationally expensive as the reflection order and room complexity increase. We propose a physics-guided framework for fast RIR simulation that preserves the geometric structure of ISM while learning to retain only acoustically important image-source paths during online traversal. To recover energy removed by pruning, the proposed PathRIR uses a lightweight compensation multilayer perceptron to predict the missing late-tail energy envelope and generate a compensation tail whose energy follows that envelope. Experiments on irregular 3D rooms show that PathRIR reduces image-source computation and improves runtime efficiency over a full-order ISM simulator, while achieving low waveform- and decay-related errors. Ablation results show that adding the compensation tail improves waveform fidelity and reduces energy-decay-curve error, reverberation-time error, and direct-to-reverberant-ratio error, with modest runtime overhead.
Shaoheng Xu, Chunyi Sun, Jihui Zhang +3
The Australian National University, Australia · The University of Queensland, Australia