Learning Acoustic Scattering Fields for Dynamic Interactive Sound Propagation

Tang, Zhenyu; Meng, Hsien-Yu; Manocha, Dinesh

doi:10.48550/arxiv.2010.04865

Cited by 2 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is challenging to handle sound propagation in large-scale, outdoor, dynamic scenes, especially in terms of generate low-frequency effects. The most accurate methods are based on wave-based propagation, but they are mostly limited to static scenes, though learning methods are promising and can approximate the scattering field of moving of moving or deforming objects [217]. (6) It is necessary to develop plausible, quantitative sound evaluation metrics in the future.…”

Section: Discussionmentioning

confidence: 99%

“…The former uses accurate numerical acoustic method for modeling, while the latter is based on a geometric method that is good at handling high-frequency sound. Hybrid numeric-geometric algorithms have been proposed to approximate diffraction and occlusion effects around smooth surfaces [176], [217]. Other hybrid method is based on combining ray tracing with reverberation filters [192], which has very low runtime computational overhead and also works well on mobile devices.…”

Section: Hybrid Methodsmentioning

confidence: 99%

“…Thus, they formulated the sound propagation as an image-to-image regression problem. Tang et al [217] proposed learning the acoustic scattering field of objects for lower frequencies from 3D geometric object information. Then, at runtime, the above learned information can be used for estimating the scattered field when sound waves interact with objects.…”

Section: Deep Learning For Sound Propagationmentioning

confidence: 99%

See 2 more Smart Citations

Sound Synthesis, Propagation, and Rendering: A Survey

Liu,

Manocha

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Sound, as a crucial sensory channel, plays a vital role in improving the reality and immersiveness of a virtual environment, following only vision in importance. Sound can provide important clues such as sound directionality and spatial size. This paper gives a broad overview of research works on sound simulation in virtual reality, games, etc. We first survey various sound synthesis methods, including harmonic synthesis, texture synthesis, spectral analysis, and physics-based synthesis. Then, we summarize popular sound propagation techniques, namely wave-based methods, geometric-based methods, and hybrid methods. Next, the sound rendering methods are reviewed. We also highlight some recent methods that use machine learning techniques for synthesis, propagation, and some inverse problems.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Hybrid Methodsmentioning

confidence: 99%

Section: Deep Learning For Sound Propagationmentioning

confidence: 99%

See 1 more Smart Citation

Sound Synthesis, Propagation, and Rendering: A Survey

Liu,

Manocha

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Determining acoustic characteristics of surfaces requires the work of expert acousticians, an obstacle to real-time rendering, which has gained increasing attention in the field of sound rendering. Recent work has approached this problem by adopting cutting edge machine learning techniques [8]- [11].…”

Section: Introductionmentioning

confidence: 99%

Acoustic Rendering Based on Geometry Reduction and Acoustic Material Classification

Colombo

Dolhasz²,

Hockman

et al. 2022

2022 IEEE Conference on Games (CoG)

View full text Add to dashboard Cite

We present work in progress on a pipeline for audio rendering integrating vision-based systems for acoustic material classification. With a marching cubes algorithm, the pipeline estimates a cuboid acoustic volume encapsulating the listener, a sound source, and the surrounding environment. A variableresolution binary field, samples and simplifies the input scene, and captures the appearance of surfaces to produce a set of image patches. A classifier infers acoustic materials, expressed as frequency-dependent acoustic absorption coefficients, from image patches. The estimated volume and aggregated acoustic materials provide input to the Image Source Model that models reverberation by generating Room Impulse Responses (RIRs). We conduct preliminary tests by applying our pipeline on a set of indoor and outdoor scenes, producing RIRs with inferred acoustic materials, comparing them against RIRs with manually assigned acoustic materials, extracting and evaluating objective metrics, such as reverberation or clarity. Through a learned metric on subjective responses, we compare perceptual aspects of automatically-generated RIRs against manually tagged. Objective and subjective analysis suggests that the pipeline can automate the acoustic material classification process by producing RIRs indistinguishable from manually-tagged counterparts.

show abstract

Learning Acoustic Scattering Fields for Dynamic Interactive Sound Propagation

Cited by 2 publications

References 40 publications

Sound Synthesis, Propagation, and Rendering: A Survey

Sound Synthesis, Propagation, and Rendering: A Survey

Acoustic Rendering Based on Geometry Reduction and Acoustic Material Classification

Contact Info

Product

Resources

About