2010 · 34 citations · 4 references
ComputingComputer Science3D ModelingComputer VisionMachine Vision3D ReconstructionCamera GeometryCamera ModelsMotion EstimationMulti-view GeometryVideo AnalysisFramesFundamental MatrixFundamental Matrix EstimationMotion Blur ReductionMotion Blur RemovalReference Frame Selection
Automatic reconstruction of 3D models from video sequences requires selection of appropriate video frames for performing the reconstruction. We introduce a complete method for key frame selection that automatically avoids degeneracies and is robust to inaccurate correspondences caused by motion blur. Our method combines selection criteria based on the number of frame-to-frame point correspondences, Torr’s geometrical robust information criterion (GRIC) scores for the frame-to-frame homography and fundamental matrix, and the point-to-epipolar line cost for the frame-to-frame point correspondence set. In a series of experiments with real and synthetic data sets, we show that our method achieves robust 3D reconstruction in the presence of noise and degenerate motion.
4
Visual Modeling with a Hand-Held Camera
Marc Pollefeys, Luc Van Gool, Maarten Vergauwen et al. · International Journal of Computer Vision · 2004 · 872 citations