Skip to main content

Characterizing Layouts of Outdoor Scenes Using Spatial Topic Processes

Author(s): Lin, Dahua; Xiao, Jianxiong

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr11c3g
Abstract: In this paper, we develop a generative model to describe the layouts of outdoor scenes - the spatial configuration of regions. Specifically, the layout of an image is represented as a composite of regions, each associated with a semantic topic. At the heart of this model is a novel stochastic process called Spatial Topic Process, which generates a spatial map of topics from a set of coupled Gaussian processes, thus allowing the distributions of topics to vary continuously across the image plane. A key aspect that distinguishes this model from previous ones consists in its capability of capturing dependencies across both locations and topics while allowing substantial variations in the layouts. We demonstrate the practical utility of the proposed model by testing it on scene classification, semantic segmentation, and layout hallucination.
Publication Date: 2013
Citation: Lin, Dahua, and Jianxiong Xiao. "Characterizing layouts of outdoor scenes using spatial topic processes." In Proceedings of the IEEE International Conference on Computer Vision (2013): pp. 841-848. doi:10.1109/ICCV.2013.109
DOI: 10.1109/ICCV.2013.109
Pages: 841 - 848
Type of Material: Conference Article
Journal/Proceeding Title: Proceedings of the IEEE International Conference on Computer Vision
Version: Author's manuscript



Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.