Reconstruction of indoor scene from a single image

Di Wu; Hongyu Li; Lin Zhang

doi:10.1117/12.2179370

4 March 2015 Reconstruction of indoor scene from a single image

Di Wu, Hongyu Li, Lin Zhang

Proceedings Volume 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014); 944325 (2015) https://doi.org/10.1117/12.2179370
Event: Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 2014, Beijing, China

Abstract

Given a single image of an indoor scene without any prior knowledge, is it possible for a computer to automatically reconstruct the structure of the scene? This letter proposes a reconstruction method, called RISSIM, to recover the 3D modelling of an indoor scene from a single image. The proposed method is composed of three steps: the estimation of vanishing points, the detection and classification of lines, and the plane mapping. To find vanishing points, a new feature descriptor, named “OCR”, is defined to describe the texture orientation. With Phrase Congruency and Harris Detector, the line segments can be detected exactly, which is a prerequisite. Perspective transform is a defined as a reliable method whereby the points on the image can be represented on a 3D model. Experimental results show that the 3D structure of an indoor scene can be well reconstructed from a single image although the available depth information is limited.

Citation Download Citation

Di Wu, Hongyu Li, and Lin Zhang "Reconstruction of indoor scene from a single image", Proc. SPIE 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 944325 (4 March 2015); https://doi.org/10.1117/12.2179370

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available