Sampling bedrooms
Authors:
- 1 June 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 2009-2016
Abstract
We propose a top down approach for understanding indoor scenes such as bedrooms and living rooms. These environments typically have the Manhattan world property that many surfaces are parallel to three principle ones. Further, the 3D geometry of the room and objects within it can largely be approximated by non overlapping simple structures such as single blocks (e.g. the room boundary), thin blocks (e.g. picture frames), and objects that are well modeled by single blocks (e.g. simple beds). We separately model the 3D geometry, the imaging process (camera parameters), and edge likelihood, to provide a generative statistical model for image data. We fit this model using data driven MCMC sampling. We combine reversible jump Metropolis Hastings samples for discrete changes in the model such as the number of blocks, and stochastic dynamics to estimate continuous parameter values in a particular parameter space that includes block positions, block sizes, and camera parameters. We tested our approach on two datasets using room box pixel orientation. Despite using only bounding box geometry and, in particular, not training on appearance, our method achieves results approaching those of others. We also introduce a new evaluation method for this domain based on ground truth camera parameters, which we found to be more sensitive to the task of understanding scene geometry.Keywords
This publication has 19 references indexed in Scilit:
- Recovering the spatial layout of cluttered rooms2009
- Building a database of 3D scenes from user annotations2009
- Geometric reasoning for single image structure recovery2009
- Image Parsing: Unifying Segmentation, Detection, and RecognitionInternational Journal of Computer Vision, 2005
- Geometric context from a single image2005
- A new method of camera pose estimation using 2D–3D corner correspondencePattern Recognition Letters, 2004
- Multiple View Geometry in Computer Vision2004
- Image segmentation by data-driven markov chain monte carloIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- Fitting parameterized three-dimensional models to imagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- Recognizing solid objects by alignment with an imageInternational Journal of Computer Vision, 1990