arXiv：cs.LG· Hyebin Cho, Bumsoo Kim, Joon son Chung·· 4 小时前AI 评分34
ImpactMat：面向逆向撞击声渲染的连续材质估计数据集与基准
ImpactMat: Continuous Material Estimation for Inverse Impact Sound Rendering
AI 导读
ImpactMat 是一个单材质与混合材质撞击声数据集与基准，配有真实材质参数，用于研究从参考撞击声逆向预测材质参数的逆向撞击声渲染任务。研究者提出一个前馈模型，可从一段或多段录音中预测材质参数，并利用混合材质学习材质类型间的平滑过渡。实验显示该方法优于竞争基线，无需手动调参即可从真实录音重新渲染。
正文
Abstract: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 this https URL.
| Comments: | Preprint |
| Subjects: | Sound (cs.SD); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.07061 [cs.SD] |
| (or arXiv:2610.07061v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07061 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hyebin Cho [view email]
[v1]
Mon, 5 Oct 2026 06:50:40 UTC (1,814 KB)
来源：arXiv：cs.LG · arxiv.org