Daniel Barath  News:  Awards:  
PhD Student Machine Perception Research Laboratory, MTA SZTAKI, Hungary, Budapest barath.daniel@sztaki.mta.hu 
2018.03.21. Two accepted papers for CVPR 2018! 2017.05.19. Source code of MultiH is available 2017.03.16: Accepted Paper for CVPR 2017! 
2017.01.26: Kuba Attila Prize 
MultiH Algorithm  Consistency of Local Affinities  Surface Normal Estimation  Homography Estimation  Focal Length Estimation 
MultiH: Efficient Recovery of Tangent Planes in Stereo Images 
Overview: MultiH  an efficient method for the recovery of the tangent planes of a set of point correspondences satisfying the epipolar constraint is proposed. The problem is formulated as a search for a labeling minimizing an energy that includes a data and spatial regularization terms. The number of planes is controlled by a combination of MeanShift and Alphaexpansion. Since the widelyused AdelaideRMF dataset seems to be easy, we propose a more challenging dataset for multihomography estimation. 
Code: C++ code 
Dataset: Annotated dataset 
Onepage abstract: PDF 
Reference paper: Barath, D. and Matas, J. and Hajder, L., MultiH: Efficient Recovery of Tangent Planes in Stereo Images. 27th British Machine Vision Conference, 2016. PDF 
Accurate Closedform Estimation of Local Affine Transformations Consistent with the Epipolar Geometry 
Overview: For a pair of images satisfying the epipolar constraint, a method for accurate estimation of local affine transformations is proposed. The method returns the local affine transformation consistent with the epipolar geometry that is closest in the least squares sense to the initial estimate provided by an affinecovariant detector. The minimized L_{2} norm of the affine matrix elements is found in closedform. We show that the used norm has an intuitive geometric interpretation. The method, with negligible computational requirements, is validated on publicly available benchmarking datasets and on synthetic data. The accuracy of the local affine transformations is improved for all detectors and all image pairs. Implicitly, precision of the tested feature detectors was compared. The HessianAffine detector combined with ASIFT view synthesis was the most accurate. 
Code: C++ code, Matlab code 
Onepage abstract: PDF 
Reference paper: Barath, D. and Matas, J. and Hajder, L., Accurate Closedform Estimation of Local Affine Transformations Consistent with the Epipolar Geometry. 27th British Machine Vision Conference, 2016. PDF 
Homography Estimation using Affine Correspondences 
Novel Ways to Estimate Homography from Local Affine Transformations 
Overview: In this paper, three novel methods for the estimation of homographies exploiting local affine transformations are proposed. The method called Homography from Affine transformation and Fundamental matrix (HAF) shows that there is a onetoone relationship between homography and local affinity for known epipolar geometry. 
Code: Matlab code 
Reference paper: Barath, D. and Hajder, L., Novel Ways to Estimate Homography from Local Affine Transformations. 11th International Conference on Computer Vision Theory and Applications, 2016. PDF 
PHAF: Homography Estimation Using Partial Local Affine Frames 
Overview: In this paper, we propose a minimal method to estimate a homography using only two SIFT correspondences. The method is realtime capable, makes homography and multihomography estimation more accurate and generalized to the overdetermined case. 
Code: Available Soon 
Reference paper: Barath, D., PHAF: Homography Estimation Using Partial Local Affine Frames. 12th International Conference on Computer Vision Theory and Applications, 2017. PDF 
Surface Normal Estimation 
Optimal Surface Normal using Affine Correspondences 
Overview: This project deals with surface normal estimation from calibrated stereo images. We have shown how the local affine transformation between two projections defines the surface normal of a 3D planar patch. We have given a formula that describes the relationship of surface normals, camera projections, and affine transformations. This formula is general since it works for every kind of cameras. We propose novel methods for estimating the normal of a surface patch if the affine transformation is known between two perspective images. Five methods published in our paper, their Matlab/Octave implementation can be downloaded. The proposed methods are as follows:

Code: Matlab code 
Reference paper: D. Baráth, J. Molnár, L. Hajder: Optimal Surface Normal from Affine Transformation, in Proc. of the 10th Intl. Joint Conf. on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), 2015. PDF 
A Minimal Solution for TwoView FocalLength Estimation Using Two Affine Correspondences 
Overview: A minimal solution using two affine correspondences is presented to estimate the common focal length and the fundamental matrix between two semicalibrated cameras  known intrinsic parameters except a common focal length. To the best of our knowledge, this problem is unsolved. The proposed approach extends point correspondencebased techniques with linear constraints derived from local affine transformations. The obtained multivariate polynomial system is efficiently solved by the hiddenvariable technique. Observing the geometry of local affinities, we introduce novel conditions eliminating invalid roots. To select the best one out of the remaining candidates, a root selection technique is proposed outperforming the recent ones especially in case of highlevel noise. The proposed 2point algorithm is validated on both synthetic data and 104 publicly available real image pairs. A Matlab implementation of the proposed solution is included in the paper. 
Code: Matlab code 
Reference paper: Daniel Barath, Tekla Toth, Levente Hajder: A Minimal Solution for TwoView FocalLength Estimation Using Two Affine Correspondences, Conference on Computer Vision and Pattern Recognition (CVPR), 2017. PDF 