RGI-Net: 3D Room Geometry Inference from Room Impulse Responses With Hidden First-Order Reflections

TL;DR

RGI-Net is a novel deep learning approach that accurately infers complex 3D room geometries from room impulse responses without relying on traditional assumptions like convexity or visible first-order reflections.

Contribution

It introduces RGI-Net, capable of estimating non-convex room shapes and wall presence without prior knowledge, overcoming limitations of conventional methods.

Findings

Successfully estimates non-convex room geometries.

Operates without prior knowledge of the number of walls.

Handles missing first-order reflections in RIRs.

Abstract

Room geometry is important prior information for implementing realistic 3D audio rendering. For this reason, various room geometry inference (RGI) methods have been developed by utilizing the time-of-arrival (TOA) or time-difference-of-arrival (TDOA) information in room impulse responses (RIRs). However, the conventional RGI technique poses several assumptions, such as convex room shapes, the number of walls known in priori, and the visibility of first-order reflections. In this work, we introduce the RGI-Net which can estimate room geometries without the aforementioned assumptions. RGI-Net learns and exploits complex relationships between low-order and high-order reflections in RIRs and, thus, can estimate room shapes even when the shape is non-convex or first-order reflections are missing in the RIRs. RGI-Net includes the evaluation network that separately evaluates the presence probability of walls, so the geometry inference is possible without prior knowledge of the number of walls.