ImpactMat: Continuous Material Estimation for Inverse Impact Sound Rendering

2026-10-05

AI Summary

This study addresses the limitations of impact sound rendering, which typically relies on discrete material presets and requires laborious manual parameter tuning. To overcome these challenges, we introduce a novel inverse impact sound rendering paradigm that infers continuous material parameters directly from audio. Methodologically, we construct the ImpactMat dataset alongside an evaluation benchmark and propose a feedforward neural network-based prediction model. By leveraging mixed-material modeling to learn smooth transitions, our approach transcends the constraints of discrete presets, enabling simulation-based re-rendering without manual intervention. Experimental results demonstrate that the proposed method outperforms baseline approaches and successfully reconstructs material responses from real-world recordings, substantially lowering the barrier for non-expert users in physically informed sound synthesis.

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 https://material-from-impact.github.io/material-from-impact/.

Problem

• inverse impact sound rendering
• material parameter estimation
• impact sound synthesis
• continuous material representation

Innovation

• Inverse Impact Sound Rendering
• Material Estimation
• ImpactMat Dataset
• Blended Materials
• Feed-forward Model