Geometric Driven Optical Flow Estimation and Segmentation for 3D Reconstruction

Authors:
Lionel Oisel;Étienne Mémin;Luce Morin
Affiliations:
-;-;-
Venue:
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part II
Year:
2000

Citing 12
Cited 0

Robust regression and outlier detection

Robust regression and outlier detection
Performance of optical flow techniques

International Journal of Computer Vision
Recursive non-linear estimation of discontinuous flow fields

ECCV '94 Proceedings of the third European conference on Computer vision (vol. 1)
On the unification of line processes, outlier rejection, and robust statistics with applications in early vision

International Journal of Computer Vision
View synthesis from unregistered 2-D images

GI '96 Proceedings of the conference on Graphics interface '96
Reliable and Efficient Computation of Optical Flow

International Journal of Computer Vision
Estimating Motion and Structure from Correspondences of Line Segments between Two Perspective Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Dense Depth Map Reconstruction: A Minimization and Regularization Approach which Preserves Discontinuities

ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Automatic 3D Model Acquisition from Uncalibrated Image Sequences

CGI '98 Proceedings of the Computer Graphics International 1998
Virtualized reality: concepts and early results

VSR '95 Proceedings of the IEEE Workshop on Representation of Visual Scenes
Epipole and fundamental matrix estimation using virtual parallax

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Deterministic edge-preserving regularization in computed imaging

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a method for fully automatic 3D reconstruction from a pair of uncalibrated images in order to deal with the modeling of complex rigid scenes. A 2D triangular mesh model of the scene is calculated using a two-step algorithm mixing sparse matching and dense motion estimation approaches. The 2D mesh is iteratively refined to fit any arbitrary 3D surface. At convergence, each triangular patch corresponds to the projection of a 3D plane. The algorithm proposed here relies first on a dense disparity field. The dense field estimation modelized within a robust framework is constrained by the epipolar geometry. The resulting field is then segmented according to homographic models using iterative Delaunay triangulation. In association with a simplified self-calibration algorithm, this 2D planar model is used to obtain a VRML-compatible 3D model of the scene.