Point2Acoustic: Efficient Room Acoustic Parameter Estimation from 3D Geometry and Material Properties

Xun Gao; Raksha Ramakrishna; Tommy Falk; Werner de Bruijn

eess.ASOct 19, 2026

Point2Acoustic: Efficient Room Acoustic Parameter Estimation from 3D Geometry and Material Properties

Authors: Xun Gao, Raksha Ramakrishna, Tommy Falk, Werner de Bruijn

Organizations: KTH Royal Institute of Technology, Stockholm, Sweden · Ericsson Research, Stockholm, Sweden

Abstract

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 ( $RT_{60}$ ) 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 $RT_{60}$ and RDR estimates using simulation-derived training targets.

	$RT_{60}$		RDR
Method	MAE $\downarrow$	$R^{2}$ $\uparrow$	MAE $\downarrow$	$R^{2}$ $\uparrow$	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.

	$RT_{60}$		RDR
Features	MAE (s) $\downarrow$	$R^{2}$ $\uparrow$	MAE (dB) $\downarrow$	$R^{2}$ $\uparrow$
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 $R^{2}$ from clean input; error bars denote mean $\pm$ standard deviation over five trials.

Room Acoustics

Room acoustics studies how spaces shape sound through reflection, absorption, reverberation, and spatial propagation.

See all 19 papers

ImpactMat: Continuous Material Estimation for Inverse Impact Sound Rendering
Oct 5, 2026Hyebin Cho, Bumsoo Kim, Joon Son ChungInverse Rendering Materials Property Prediction
Korea Advanced Institute of Science and Technology, South Korea · Chung-Ang University, South Korea
What does the model actually see? Evaluation protocols and input availability in data-driven prediction of room acoustic parameters
Jul 16, 2026Ak\in OktavBenchmark Design Room Acoustics
Vibration and Acoustics Laboratory (VAL) and Department of Mechanical Engineering, Alanya Alaaddin Keykubat University, 07425, Antalya, Türkiye
PathRIR: Physics-Guided Acoustic Path Selection and Late-Tail Compensation for Fast Room Impulse Response Simulation
Jul 25, 2026Shaoheng Xu, Chunyi Sun, Jihui Zhang +3Physics-Informed ML Spatial Audio
The Australian National University, Australia · The University of Queensland, Australia

Oct 5, 2026J/K move · Enter open · S save

ImpactMat: Continuous Material Estimation for Inverse Impact Sound Rendering

Hyebin Cho, Bumsoo Kim, Joon Son Chung

Korea Advanced Institute of Science and Technology, South Korea · Chung-Ang University, South Korea

Inverse Rendering Materials Property Prediction

Open paper AskPDF arXiv

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/.

Abstract

Room Acoustics

Explore similar work

ImpactMat: Continuous Material Estimation for Inverse Impact Sound Rendering

What does the model actually see? Evaluation protocols and input availability in data-driven prediction of room acoustic parameters

PathRIR: Physics-Guided Acoustic Path Selection and Late-Tail Compensation for Fast Room Impulse Response Simulation