VAIR: Visuo-Acoustic Implicit Representations for Low-Cost, Multi-Modal Transparent Surface Reconstruction in Indoor Scenes
Mobile robots operating indoors must be prepared to navigate challenging scenes that contain transparent surfaces. This paper proposes a novel method for the fusion of acoustic and visual sensing modalities through implicit neural representations to enable dense reconstruction of transparent surface...
Gespeichert in:
Hauptverfasser: | , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Mobile robots operating indoors must be prepared to navigate challenging
scenes that contain transparent surfaces. This paper proposes a novel method
for the fusion of acoustic and visual sensing modalities through implicit
neural representations to enable dense reconstruction of transparent surfaces
in indoor scenes. We propose a novel model that leverages generative latent
optimization to learn an implicit representation of indoor scenes consisting of
transparent surfaces. We demonstrate that we can query the implicit
representation to enable volumetric rendering in image space or 3D geometry
reconstruction (point clouds or mesh) with transparent surface prediction. We
evaluate our method's effectiveness qualitatively and quantitatively on a new
dataset collected using a custom, low-cost sensing platform featuring RGB-D
cameras and ultrasonic sensors. Our method exhibits significant improvement
over state-of-the-art for transparent surface reconstruction. |
---|---|
DOI: | 10.48550/arxiv.2411.04963 |