Deep3DLayout: 3D Reconstruction of an Indoor Layout from a Spherical Panoramic Image

Giovanni Pintore, Eva Almansa, Marco Agus, Enrico Gobbetti

Research output: Contribution to journalArticlepeer-review

21 Citations (Scopus)

Abstract

Recovering the 3D shape of the bounding permanent surfaces of a room from a single image is a key component of indoor reconstruction pipelines. In this article, we introduce a novel deep learning technique capable to produce, at interactive rates, a tessellated bounding 3D surface from a single 360 image. Differently from prior solutions, we fully address the problem in 3D, significantly expanding the reconstruction space of prior solutions. A graph convolutional network directly infers the room structure as a 3D mesh by progressively deforming a graph-encoded tessellated sphere mapped to the spherical panorama, leveraging perceptual features extracted from the input image. Important 3D properties of indoor environments are exploited in our design. In particular, gravity-aligned features are actively incorporated in the graph in a projection layer that exploits the recent concept of multi head self-attention, and specialized losses guide towards plausible solutions even in presence of massive clutter and occlusions. Extensive experiments demonstrate that our approach outperforms current state of the art methods in terms of accuracy and capability to reconstruct more complex environments.

Original languageEnglish
Article number250
JournalACM Transactions on Graphics
Volume40
Issue number6
DOIs
Publication statusPublished - 10 Dec 2021

Keywords

  • data-driven reconstruction
  • indoor 3D layout
  • panoramic images
  • structured indoor reconstruction

Fingerprint

Dive into the research topics of 'Deep3DLayout: 3D Reconstruction of an Indoor Layout from a Spherical Panoramic Image'. Together they form a unique fingerprint.

Cite this