Least Commitment, Viewpoint-Based, Multi-view Stereo
Authors:
- Xiaoyan HuXHXiaoyan Hu
- Philippos MordohaiPMPhilippos Mordohai
- 1 October 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 531-538
Abstract
We address the problem of large-scale 3D reconstruction from calibrated images relying on a viewpoint-based approach. The representation is in the form of a collection of depth maps, which are fused to blend consistent depth estimates and minimize violations of visibility constraints. We adopt a least commitment strategy by allowing multiple candidate depth values per pixel in the fusion process and deferring hard decisions as much as possible. To address the inevitable noise in the depth maps, we explicitly model its sources, namely mismatches and inaccurate 3D coordinate estimation via triangulation, by measuring two types of uncertainty and using the uncertainty estimates to guide the fusion process. To the best of our knowledge, this is the first attempt to model both geometric and correspondence uncertainty in the context of dense 3D reconstruction. We show quantitative results on datasets with ground truth that are competitive with the state of the art.Keywords
This publication has 23 references indexed in Scilit:
- Video-based, real-time multi-view stereoImage and Vision Computing, 2011
- Multi-view Superpixel Stereo in Urban EnvironmentsInternational Journal of Computer Vision, 2010
- Reconstructing relief surfacesImage and Vision Computing, 2008
- Detailed Real-Time Urban 3D Reconstruction from VideoInternational Journal of Computer Vision, 2007
- Real-Time Plane-Sweeping Stereo with Multiple Sweeping Directions2007
- Multi-View Stereo Reconstruction and Scene Flow Estimation with a Global Image-Based Matching ScoreInternational Journal of Computer Vision, 2006
- Uncertainty and Projective Geometry2005
- Silhouette and stereo fusion for 3D object modelingComputer Vision and Image Understanding, 2004
- A volumetric method for building complex models from range images1996
- Zippered polygon meshes from range images1994