TechTalks from event: CVPR 2014 Oral Talks

Orals 1A : Matching & Reconstruction

  • Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction Authors: Jian Cheng, Cong Leng, Jiaxiang Wu, Hainan Cui, Hanqing Lu
    Image matching is one of the most challenging stages in 3D reconstruction, which usually occupies half of computational cost and inaccurate matching may lead to failure of reconstruction. Therefore, fast and accurate image matching is very crucial for 3D reconstruction. In this paper, we proposed a Cascade Hashing strategy to speed up the image matching. In order to accelerate the image matching, the proposed Cascade Hashing method is designed to be three-layer structure: hashing lookup, hashing remapping, and hashing ranking. Each layer adopts different measures and filtering strategies, which is demonstrated to be less sensitive to noise. Extensive experiments show that image matching can be accelerated by our approach in hundreds times than brute force matching, even achieves ten times or more than Kd-tree based matching while retaining comparable accuracy.
  • Predicting Matchability Authors: Wilfried Hartmann, Michal Havlena, Konrad Schindler
    The initial steps of many computer vision algorithms are interest point extraction and matching. In larger image sets the pairwise matching of interest point descriptors between images is an important bottleneck. For each descriptor in one image the (approximate) nearest neighbor in the other one has to be found and checked against the second-nearest neighbor to ensure the correspondence is unambiguous. Here, we asked the question how to best decimate the list of interest points without losing matches, i.e. we aim to speed up matching by filtering out, in advance, those points which would not survive the matching stage. It turns out that the best filtering criterion is not the response of the interest point detector, which in fact is not surprising: the goal of detection are repeatable and well-localized points, whereas the objective of the selection are points whose descriptors can be matched successfully. We show that one can in fact learn to predict which descriptors are matchable, and thus reduce the number of interest points significantly without losing too many matches. We show that this strategy, as simple as it is, greatly improves the matching success with the same number of points per image. Moreover, we embed the prediction in a state-of-the-art Structure-from-Motion pipeline and demonstrate that it also outperforms other selection methods at system level.
  • Trinocular Geometry Revisited Authors: Jean Ponce, Martial Hebert
    When do the visual rays associated with triplets of point correspondences converge, that is, intersect in a common point? Classical models of trinocular geometry based on the fundamental matrices and trifocal tensor associated with the corresponding cameras only provide partial answers to this fundamental question, in large part because of underlying, but seldom explicit, general configuration assumptions. This paper uses elementary tools from projective line geometry to provide necessary and sufficient geometric and analytical conditions for convergence in terms of transversals to triplets of visual rays, without any such assumptions. In turn, this yields a novel and simple minimal parameterization of trinocular geometry for cameras with non-collinear or collinear pinholes.
  • Critical Configurations For Radial Distortion Self-Calibration Authors: Changchang Wu
    In this paper, we study the configurations of motion and structure that lead to inherent ambiguities in radial distortion estimation (or 3D reconstruction with unknown radial distortions). By analyzing the motion field of radially distorted images, we solve for critical surface pairs that can lead to the same motion field under different radial distortions and possibly different camera motions. We study the properties of the discovered critical configurations and discuss the practically important configurations that often occur in real applications. We demonstrate the impact of the radial distortion ambiguity on multi-view reconstruction with synthetic experiments and real experiments.
  • Minimal Solvers for Relative Pose with a Single Unknown Radial Distortion Authors: Yubin Kuang, Jan Erik Solem, Fredrik Kahl, Kalle Åström
    In this paper, we study the problems of estimating relative pose between two cameras in the presence of radial distortion. Specifically, we consider minimal problems where one of the cameras has no or known radial distortion. There are three useful cases for this setup with a single unknown distortion: (i) fundamental matrix estimation where the two cameras are uncalibrated, (ii) essential matrix estimation for a partially calibrated camera pair, (iii) essential matrix estimation for one calibrated camera and one camera with unknown focal length. We study the parameterization of these three problems and derive fast polynomial solvers based on Gr{\"o}bner basis methods. We demonstrate the numerical stability of the solvers on synthetic data. The minimal solvers have also been applied to real imagery with convincing results
  • Reconstructing PASCAL VOC Authors: Sara Vicente, João Carreira, Lourdes Agapito, Jorge Batista
    We address the problem of populating object category detection datasets with dense, per-object 3D reconstructions, bootstrapped from class labels, ground truth figure-ground segmentations and a small set of keypoint annotations. Our proposed algorithm first estimates camera viewpoint using rigid structure-from-motion, then reconstructs object shapes by optimizing over visual hull proposals guided by loose within-class shape similarity assumptions. The visual hull sampling process attempts to intersect an object's projection cone with the cones of minimal subsets of other similar objects among those pictured from certain vantage points. We show that our method is able to produce convincing per-object 3D reconstructions on one of the most challenging existing object-category detection datasets, PASCAL VOC. Our results may re-stimulate once popular geometry-oriented model-based recognition approaches.