Echo-Reconstruction: Audio-Augmented 3D Scene Reconstruction

TL;DR

This paper introduces Echo-Reconstruction, an audio-visual method that leverages sound reflections to improve 3D scene reconstruction, especially around reflective and textureless surfaces, enhancing visual and audio fidelity in AR/VR applications.

Contribution

It presents a novel audio-visual neural network approach that uses sound reflections to improve depth estimation and scene reconstruction involving challenging surfaces.

Findings

High accuracy in material classification

Effective depth estimation around reflective surfaces

Significant improvement in 3D scene quality

Abstract

Reflective and textureless surfaces such as windows, mirrors, and walls can be a challenge for object and scene reconstruction. These surfaces are often poorly reconstructed and filled with depth discontinuities and holes, making it difficult to cohesively reconstruct scenes that contain these planar discontinuities. We propose Echoreconstruction, an audio-visual method that uses the reflections of sound to aid in geometry and audio reconstruction for virtual conferencing, teleimmersion, and other AR/VR experience. The mobile phone prototype emits pulsed audio, while recording video for RGB-based 3D reconstruction and audio-visual classification. Reflected sound and images from the video are input into our audio (EchoCNN-A) and audio-visual (EchoCNN-AV) convolutional neural networks for surface and sound source detection, depth estimation, and material classification. The inferences from these classifications enhance scene 3D reconstructions containing open spaces and reflective surfaces by depth filtering, inpainting, and placement of unmixed sound sources in the scene. Our prototype, VR demo, and experimental results from real-world and virtual scenes with challenging surfaces and sound indicate high success rates on classification of material, depth estimation, and closed/open surfaces, leading to considerable visual and audio improvement in 3D scenes (see Figure 1).