Complete 3D Scene Parsing from an RGBD Image

Chuhang Zou, Ruiqi Guo, Zhizhong Li, Derek Hoiem

Research output: Contribution to journalArticlepeer-review

Abstract

One major goal of vision is to infer physical models of objects, surfaces, and their layout from sensors. In this paper, we aim to interpret indoor scenes from one RGBD image. Our representation encodes the layout of orthogonal walls and the extent of objects, modeled with CAD-like 3D shapes. We parse both the visible and occluded portions of the scene and all observable objects, producing a complete 3D parse. Such a scene interpretation is useful for robotics and visual reasoning, but difficult to produce due to the well-known challenge of segmentation, the high degree of occlusion, and the diversity of objects in indoor scenes. We take a data-driven approach, generating sets of potential object regions, matching to regions in training images, and transferring and aligning associated 3D models while encouraging fit to observations and spatial consistency. We use support inference to aid interpretation and propose a retrieval scheme that uses convolutional neural networks to classify regions and retrieve objects with similar shapes. We demonstrate the performance of our method on our newly annotated NYUd v2 dataset (Silberman et al., in: Computer vision-ECCV, 2012, pp 746–760, 2012) with detailed 3D shapes.

Original languageEnglish (US)
Pages (from-to)143-162
Number of pages20
JournalInternational Journal of Computer Vision
Volume127
Issue number2
DOIs
StatePublished - Feb 15 2019

Keywords

  • 3D parsing
  • Single image reconstruction
  • Visual scene understanding

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Complete 3D Scene Parsing from an RGBD Image'. Together they form a unique fingerprint.

Cite this