Abstract
The task of inferring the 3D layout of indoor scenes from images has seen many recent advancements. Understanding the basic 3D geometry of these environments is important for higher level applications, such as object recognition and robot navigation. In this chapter, we present our Bayesian generative model for understanding indoor environments. We model the 3D geometry of a room and the objects within it with non-overlapping 3D boxes, which provide approximations for both the room boundary and objects like tables and beds. We separately model the imaging process (camera parameters), and an image likelihood, thus providing a complete, generative statistical model for image data. A key feature of this work is using prior information and constraints on the 3D geometry of the scene elements, which addresses ambiguities in the imaging process in a top–down fashion. We also describe and relate this work to other state-of-the-art approaches, and discuss techniques that have become standard in this field, such as estimating the camera pose from a triplet of vanishing points.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Coughlan JM, Yuille AL (1999) Manhattan world: compass direction from a single image by Bayesian inference. In: ICCV
Del Pero L, Guan J, Brau E, Schlecht J, Barnard K (2011) Sampling bedrooms. In: CVPR
Del Pero L, Bowdish J, Fried D, Kermgard B, Hartley E, Barnard K (2012) Bayesian geometric modeling of indoor scenes. In: CVPR
Delage E, Lee HL, Ng AY (2005) Automatic single-image 3d reconstructions of indoor Manhattan world scenes. In: ISRR
Green PJ (1995) Reversible jump Markov chain Monte Carlo computation and Bayesian model determination. Biometrika 82(4):711–732
Green PJ (2003) Trans-dimensional Markov chain Monte Carlo. In: Highly structured stochastic systems
Gupta A, Satkin S, Efros AA, Hebert M (2011) From 3D scene geometry to human workspace. In: CVPR
Hartley RI, Zisserman A (2004) Multiple view geometry in computer vision. Cambridge University Press, Cambridge
Hedau V, Hoiem D, Forsyth D (2009) Recovering the spatial layout of cluttered rooms. In: ICCV
Hedau V, Hoiem D, Forsyth D (2010) Thinking inside the box: using appearance models and context based on room geometry. In: ECCV
Hedau V, Hoiem D, Forsyth D (2012) Recovering free space of indoor scenes from a single image. In: CVPR
Hoiem D, Efros AA, Hebert M (2005) Geometric context from a single image. In: ICCV
Hoiem D, Efros AA, Hebert M (2006) Putting objects in perspective. In: CVPR
Karsch K, Hedau V, Forsyth D, Hoiem D (2011) Rendering synthetic objects into legacy photographs. In: SIGGRAPH Asia
Lee DC, Hebert M, Kanade T (2009) Geometric reasoning for single image structure recovery. In: CVPR
Lee DC, Gupta A, Hebert M, Kanade T (2010) Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces. In: NIPS
Neal RM (1993) Probabilistic inference using Markov chain Monte Carlo methods. Technical report
Rother C (2002) A new approach to vanishing point detection in architectural. Image Vis Comput 20(9–10):647–655
Schlecht J, Barnard K (2009) Learning models of object structure. In: NIPS
Schwing A, Hazan T, Pollefeys M, Urtasun R (2012) Efficient structure prediction with latent variables for general graphics models. In: CVPR
Shi F, Zhang X, Liu Y (2004) A new method of camera pose estimation using 2D-3D corner correspondence. Pattern Recognit Lett 25(10):1155–1163
Tsai G, Xu C, Liu J, Kuipers B (2011) Real-time indoor scene understanding using Bayesian filtering with motion cues. In: ICCV
Tu Z, Zhu S (2002) Image segmentation by data-driven Markov chain Monte-Carlo. In: PAMI
Wang H, Gould S, Koller D (2010) Discriminative learning with latent variables for cluttered indoor scene understanding. In: ECCV
Yu SX, Zhang H, Malik J (2008) Inferring spatial layout from a single image via depth-ordered grouping, In: POCV
Zhu S-C, Zhang R, Tu Z (2000) Integrating top–down/bottom–up for object recognition by data driven Markov chain Monte Carlo. In: CVPR
Acknowledgements
This material is based upon work supported by the National Science Foundation under Grant No. 0747511. We thank Joseph Schlecht for his contributions and suggestions in designing the code base. We also acknowledge the valuable help of Joshua Bowdish, Ernesto Brau, Andrew Emmott, Daniel Fried, Jinyan Guan, Emily Hartley, Bonnie Kermgard, and Philip Lee.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag London
About this chapter
Cite this chapter
Del Pero, L., Barnard, K. (2013). Top–Down Bayesian Inference of Indoor Scenes. In: Farinella, G., Battiato, S., Cipolla, R. (eds) Advanced Topics in Computer Vision. Advances in Computer Vision and Pattern Recognition. Springer, London. https://doi.org/10.1007/978-1-4471-5520-1_10
Download citation
DOI: https://doi.org/10.1007/978-1-4471-5520-1_10
Publisher Name: Springer, London
Print ISBN: 978-1-4471-5519-5
Online ISBN: 978-1-4471-5520-1
eBook Packages: Computer ScienceComputer Science (R0)