Outlier Removal for Sparse 3D Reconstruction from Video

In this work, a comparative study on sparse metric 3D reconstruction from typical video content is presented. Experimental tests are performed in order to evaluate the performances of competing algorithms from the literature in several stages of 3D reconstruction, such as feature detection and epipolar geometry estimation. During the simulations, competing algorithms, such as SIFT and Harris corner detector, PROSAC and RANSAC, 7-point and 8-point algorithms, are tested on various video content, such as TV broadcasts or recording by a hand-held camera in a controlled environment. Based on these results, it could be concluded that SIFT yields significant improvements over Harris in terms of the quality of correspondences between frames, whereas RANSAC and PROSAC perform similarly for the case of limited outliers. Finally, 7-point algorithm yields slightly superior results over 8-point. In addition to this comparative study, a novel method for the elimination of erroneous points from the reconstructed scene is proposed. The quality of the resulting algorithm is quite acceptable for its 3D reconstruction.