Skip to main content

Shape Anchors for Data-Driven Multi-view Reconstruction

Author(s): Owens, Andrew; Xiao, Jianxiong; Torralba, Antonio; Freeman, William

To refer to this page use:
Abstract: We present a data-driven method for building dense 3D reconstructions using a combination of recognition and multi-view cues. Our approach is based on the idea that there are image patches that are so distinctive that we can accurately estimate their latent 3D shapes solely using recognition. We call these patches shape anchors, and we use them as the basis of a multi-view reconstruction system that transfers dense, complex geometry between scenes. We "anchor" our 3D interpretation from these patches, using them to predict geometry for parts of the scene that are relatively ambiguous. The resulting algorithm produces dense reconstructions from stereo point clouds that are sparse and noisy, and we demonstrate it on a challenging dataset of real-world, indoor scenes.
Publication Date: 2013
Citation: Owens, Andrew, Jianxiong Xiao, Antonio Torralba, and William Freeman. "Shape Anchors for Data-Driven Multi-view Reconstruction." In IEEE International Conference on Computer Vision (2013): pp. 33-40. doi:10.1109/ICCV.2013.461
DOI: 10.1109/ICCV.2013.461
Pages: 33 - 40
Type of Material: Conference Article
Journal/Proceeding Title: 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.